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. 36172
    Prev
    Next
    INDEX
    Explanations

    different 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
    威胁
    -0.08
     Prince
    -0.08
    -Smith
    -0.08
     Evo
    -0.08
    츄
    -0.07
    peror
    -0.07
    chants
    -0.07
     adidas
    -0.07
     swords
    -0.07
    英才
    -0.07
    POSITIVE LOGITS
     Fey
    0.08
     fals
    0.07
     информ
    0.07
    formatted
    0.07
    有效性
    0.07
    答辩
    0.07
     Shak
    0.07
    Altern
    0.06
     форма
    0.06
     Outer
    0.06
    Activations Density 1.149%

    No Known Activations