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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24595
    Prev
    Next
    INDEX
    Explanations

    code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    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
     Vlad
    -0.07
    ⠩
    -0.07
    ,X
    -0.06
     wartime
    -0.06
    uire
    -0.06
    ㎚
    -0.06
    osaur
    -0.06
    jpg
    -0.06
     Серг
    -0.06
    WASHINGTON
    -0.06
    POSITIVE LOGITS
     alignSelf
    0.07
    amentos
    0.07
     usu
    0.07
    _acc
    0.07
    坤
    0.07
     unique
    0.07
     Spanish
    0.07
     parameters
    0.07
    _PATH
    0.06
     fund
    0.06
    Activations Density 0.056%

    No Known Activations