© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 21995
    Prev
    Next
    INDEX
    Explanations

    articles, "By" author name

    np_max-act · gemini-2.0-flash

    This neuron detects article metadata at the top of news pieces — headline, byline, dateline, and related header elements.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FIG
    -0.08
     Gig
    -0.07
     Asia
    -0.07
     Lisp
    -0.07
    FIG
    -0.07
     Perl
    -0.06
    tie
    -0.06
    帏
    -0.06
     incre
    -0.06
     Become
    -0.06
    POSITIVE LOGITS
     dùng
    0.08
    花样
    0.07
     mesmo
    0.07
    طرق
    0.07
    منت
    0.07
     totalCount
    0.07
    כת
    0.07
     מאוד
    0.07
    휨
    0.07
    ılması
    0.07
    Activations Density 0.076%

    No Known Activations