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. 128102
    Prev
    Next
    INDEX
    Explanations

    present

    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
    托运
    -0.08
    自主研发
    -0.08
     Canter
    -0.08
    一头
    -0.07
    iteration
    -0.07
     onload
    -0.07
    ȧ
    -0.07
    rstrip
    -0.07
     employing
    -0.07
     terminating
    -0.07
    POSITIVE LOGITS
     INT
    0.07
    膜
    0.07
    党的
    0.07
    막
    0.07
     wall
    0.06
    둥
    0.06
    긋
    0.06
    时间和
    0.06
     /
    0.06
    腊
    0.06
    Activations Density 0.012%

    No Known Activations