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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 27969
    Prev
    Next
    INDEX
    Explanations

    Names/Database entries

    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
    顺畅
    -0.07
    受损
    -0.07
    Authenticated
    -0.07
    _predict
    -0.06
    在市场上
    -0.06
    	Delete
    -0.06
    <IActionResult
    -0.06
    	win
    -0.06
    实践中
    -0.06
     Approximately
    -0.06
    POSITIVE LOGITS
    .binary
    0.07
    Hours
    0.07
    (program
    0.06
    erral
    0.06
     plant
    0.06
    .Require
    0.06
    rieben
    0.06
    ''
    0.06
    blank
    0.06
    '(
    0.06
    Activations Density 0.018%

    No Known Activations