© 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. 25-TRANSCODER-HP
    7. 107830
    Prev
    Next
    INDEX
    Explanations

    instances, examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĥĮä¸Ĭ
    -0.26
    åģ»
    -0.25
    yc
    -0.25
    .require
    -0.25
    iator
    -0.24
    halten
    -0.24
    urator
    -0.24
    LCD
    -0.24
     MES
    -0.24
    yt
    -0.23
    POSITIVE LOGITS
    ates
    0.31
    çĤ¯
    0.27
    agens
    0.27
    大åѦæ¯ķä¸ļ
    0.26
     where
    0.26
    icum
    0.26
     Instances
    0.26
    涫
    0.26
    æľ¬åĽ½
    0.26
    æĥħå½¢
    0.25
    Activations Density 0.905%

    No Known Activations