Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 72546
    Prev
    Next
    INDEX
    Explanations

    Written article/blog context

    np_max-act-logits · gemini-2.0-flash

    detailed informational and explanatory content that provides substantive descriptions or analysis of a topic.

    oai_token-act-pair · claude-4-5-haikuTriggered by @xiaoqingsun004
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝖐
    -0.08
    perator
    -0.07
    toLocale
    -0.06
     rhetoric
    -0.06
     valida
    -0.06
    ime
    -0.06
    שלום
    -0.06
     promotion
    -0.06
    odia
    -0.06
     prima
    -0.06
    POSITIVE LOGITS
    לוו
    0.08
    _ang
    0.07
    越來
    0.07
    -di
    0.06
    -mf
    0.06
    一根
    0.06
     Implemented
    0.06
    หล
    0.06
    …)
    0.06
     BOOT
    0.06
    Activations Density 3.087%

    No Known Activations