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. 19-RESID-POST-AA
    6. 3217
    Prev
    Next
    INDEX
    Explanations

    issues

    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
    鹂
    -0.08
     voksen
    -0.08
    itemName
    -0.07
    产业升级
    -0.07
    .setParent
    -0.07
    述职
    -0.06
    (arguments
    -0.06
     שאת
    -0.06
    $select
    -0.06
    焖
    -0.06
    POSITIVE LOGITS
    _duplicates
    0.08
    )'],↵
    0.07
    が多く
    0.07
     Ultra
    0.07
    ];↵
    0.07
    IntegerField
    0.07
    _w
    0.07
    NSUserDefaults
    0.07
     Wh
    0.07
    "]);↵
    0.06
    Activations Density 0.009%

    No Known Activations