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. 130891
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ?a
    -0.08
    aven
    -0.07
     בהם
    -0.07
    gf
    -0.07
    列表
    -0.07
    灯火
    -0.07
     affair
    -0.07
    烺
    -0.07
     durations
    -0.07
    芙
    -0.07
    POSITIVE LOGITS
     Wein
    0.07
     nhận
    0.07
     wrestling
    0.07
    잪
    0.06
    kul
    0.06
    瑞士
    0.06
     главное
    0.06
     kap
    0.06
     worst
    0.06
    ขน
    0.06
    Activations Density 0.003%

    No Known Activations