© 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. 15-RESID-POST-AA
    11. 2161
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash

    the coordinating conjunction that links words, phrases, or clauses, especially in formal disclaimer-style sentences.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Newsp
    -0.08
     мероп
    -0.08
    �
    -0.08
    .GetSize
    -0.07
     xảy
    -0.07
    angel
    -0.07
    班长
    -0.07
    _SUP
    -0.07
    쁘
    -0.07
    白雪
    -0.07
    POSITIVE LOGITS
    thumbs
    0.07
     "")
↵
    0.07
    ='';↵
    0.07
    $info
    0.07
     качество
    0.07
     Incorpor
    0.07
    匹配
    0.07
    :req
    0.07
     הו
    0.07
     +"
    0.06
    Activations Density 0.089%

    No Known Activations