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. 23-RESID-POST-AA
    6. 131043
    Prev
    Next
    INDEX
    Explanations

    Math regressions and equations

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dİ
    -0.07
    醯
    -0.07
    Orders
    -0.07
    .Many
    -0.07
    (Board
    -0.07
     oleh
    -0.07
     деятель
    -0.07
    forcement
    -0.07
     FindObjectOfType
    -0.07
    ////////////////////////////////////////////////////////////////////////////////
    -0.07
    POSITIVE LOGITS
     Emails
    0.07
     Searches
    0.06
     keyboard
    0.06
    ❰
    0.06
    _MARKER
    0.06
     conceptual
    0.06
    _cookies
    0.06
    (source
    0.06
    𝒕
    0.06
    .samples
    0.06
    Activations Density 0.076%

    No Known Activations