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. 59520
    Prev
    Next
    INDEX
    Explanations

    more

    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
     pur
    -0.07
     פרסום
    -0.07
     Creator
    -0.07
    とりあ
    -0.07
    ぶり
    -0.07
    ━━
    -0.06
     clin
    -0.06
     newly
    -0.06
    人气
    -0.06
     nuisance
    -0.06
    POSITIVE LOGITS
    .special
    0.07
    环球
    0.07
    äre
    0.07
    苏联
    0.07
    _marks
    0.07
    ._
    0.07
    康
    0.07
    _have
    0.07
    /of
    0.07
    證明
    0.07
    Activations Density 0.008%

    No Known Activations