Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 85109
    Prev
    Next
    INDEX
    Explanations

    Code/data serialization fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     View
    -0.08
    .FromSeconds
    -0.08
     Johann
    -0.07
    Consider
    -0.07
    licken
    -0.07
    perform
    -0.07
    .Url
    -0.07
     Locate
    -0.07
     Burl
    -0.07
    attention
    -0.07
    POSITIVE LOGITS
    电影节
    0.07
     ביק
    0.07
    赔
    0.07
    อะ
    0.07
    מול
    0.07
    🎥
    0.06
    ピン
    0.06
    这家伙
    0.06
    -unit
    0.06
     jed
    0.06
    Activations Density 0.139%

    No Known Activations