© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22235
    Prev
    Next
    INDEX
    Explanations

    food, cooking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ziej
    -0.27
    éĹ´éļĶ
    -0.26
     Tart
    -0.26
     dong
    -0.24
    飧
    -0.24
     Vera
    -0.24
    ä»»åĬ¡
    -0.24
    piring
    -0.24
     Reef
    -0.24
     Visa
    -0.23
    POSITIVE LOGITS
    积
    0.30
     pass
    0.27
    主è§Ĥ
    0.27
    eni
    0.26
    Pri
    0.25
    pass
    0.25
    ç£Ķ
    0.25
    çļĦçĶŁæ´»
    0.24
    ÑĢÑĥж
    0.24
    leys
    0.24
    Activations Density 0.003%

    No Known Activations