© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 116730
    Prev
    Next
    INDEX
    Explanations

    Development

    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
     ventana
    -0.08
    :',
    -0.07
     gt
    -0.07
    ß
    -0.07
    ò
    -0.07
     felt
    -0.07
     KW
    -0.07
    цу
    -0.06
     SUBSTITUTE
    -0.06
    ｔ
    -0.06
    POSITIVE LOGITS
    炮
    0.08
     ]↵↵
    0.07
     필요
    0.07
    (Collision
    0.06
    Degrees
    0.06
    航空
    0.06
    个交易
    0.06
    .Circle
    0.06
    加倍
    0.06
     welded
    0.06
    Activations Density 0.001%

    No Known Activations