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. 19-RESID-POST-AA
    6. 36226
    Prev
    Next
    INDEX
    Explanations

    Legal disputes/contracts

    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
    的巨大
    -0.07
    蒎
    -0.07
    懈
    -0.07
    意识到
    -0.07
    睫
    -0.07
    빚
    -0.07
    Gay
    -0.07
    uniacid
    -0.07
    ساعد
    -0.07
    活着
    -0.07
    POSITIVE LOGITS
    ERO
    0.08
     Waist
    0.07
    isches
    0.07
    ประส
    0.07
     endereco
    0.07
     Albums
    0.07
    _checkpoint
    0.07
    Parallel
    0.07
     themes
    0.07
     bombs
    0.07
    Activations Density 0.018%

    No Known Activations