© 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. 89381
    Prev
    Next
    INDEX
    Explanations

    stories and online content

    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
    亿åħĥ以ä¸Ĭ
    -0.30
    åĨ¤
    -0.28
     sting
    -0.27
    è¿ĶåĽŀæIJľçĭIJ
    -0.26
    ħĮ
    -0.26
    opies
    -0.26
    以ä¸ĬåѦåİĨ
    -0.25
     nightly
    -0.24
    .physics
    -0.24
    STALL
    -0.24
    POSITIVE LOGITS
     moments
    0.29
    ugo
    0.26
    lef
    0.25
    clo
    0.25
    åĿļæĮģ
    0.24
    æľīäºĨ
    0.24
    ä¸ļ
    0.24
    éĤ£ä¸ĢåĪ»
    0.23
    èĻļ
    0.23
     moment
    0.23
    Activations Density 2.790%

    No Known Activations