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. 71588
    Prev
    Next
    INDEX
    Explanations

    the

    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
     mejorar
    -0.08
    wdx
    -0.07
    法庭
    -0.07
    破碎
    -0.07
    有所不同
    -0.07
     Sullivan
    -0.07
    จอง
    -0.07
    破产
    -0.06
     CHUNK
    -0.06
    -align
    -0.06
    POSITIVE LOGITS
     ears
    0.07
     hire
    0.07
    利息
    0.07
     цвет
    0.07
    _exchange
    0.07
    _brand
    0.07
     Obl
    0.07
    .Exp
    0.07
     glam
    0.07
    تك
    0.07
    Activations Density 0.114%

    No Known Activations