© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 89897
    Prev
    Next
    INDEX
    Explanations

    morb

    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
     UITableViewController
    -0.07
    frm
    -0.07
    谌
    -0.07
     crypt
    -0.07
    诸葛亮
    -0.07
     Da
    -0.07
     dee
    -0.06
    payer
    -0.06
     Consumers
    -0.06
    Payments
    -0.06
    POSITIVE LOGITS
    _DEST
    0.08
     ℕ
    0.08
     <+
    0.07
    .reset
    0.07
    "]."
    0.07
    _LOOP
    0.07
    .Rectangle
    0.07
    安く
    0.07
    .Assertions
    0.06
    .DATE
    0.06
    Activations Density 0.003%

    No Known Activations