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. 11-RESID-POST-AA
    6. 25827
    Prev
    Next
    INDEX
    Explanations

    sister

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IO
    -0.07
    惊人
    -0.07
    山东
    -0.07
     novo
    -0.06
    סיס
    -0.06
     hf
    -0.06
     sizeof
    -0.06
    -record
    -0.06
    一幕
    -0.06
     pw
    -0.06
    POSITIVE LOGITS
    kins
    0.08
     -->↵↵↵
    0.07
    妩
    0.07
     LDS
    0.07
    煽
    0.07
    _icon
    0.07
    _LEFT
    0.07
     encyclopedia
    0.07
    wró
    0.07
    topl
    0.07
    Activations Density 0.014%

    No Known Activations