© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88732
    Prev
    Next
    INDEX
    Explanations

    warranty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    มà¸Ļ
    -0.24
    nim
    -0.24
     Later
    -0.24
    conds
    -0.23
     repetition
    -0.23
     later
    -0.23
     rulings
    -0.23
     ("-
    -0.23
     withdrew
    -0.23
    ä¸Ģåı¥
    -0.23
    POSITIVE LOGITS
    Ñīи
    0.26
    èĥĮä¸Ĭ
    0.25
    /value
    0.25
    è°ģéĥ½
    0.25
    avier
    0.24
     propri
    0.24
    è¿ĻäºĽéĥ½æĺ¯
    0.24
    igs
    0.24
    æľīä»·åĢ¼
    0.23
    /octet
    0.23
    Activations Density 1.981%

    No Known Activations