© 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. 19-TRANSCODER-HP
    7. 8581
    Prev
    Next
    INDEX
    Explanations

    code, math, and database

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     drive
    -0.26
    驱åĬ¨
    -0.26
    gó
    -0.25
    /drivers
    -0.24
    clusive
    -0.24
    åĻ©
    -0.24
    drive
    -0.24
     drivers
    -0.23
    çĹķ
    -0.23
    驳
    -0.23
    POSITIVE LOGITS
    åħ«å¤§
    0.27
    çļĦæł·åŃIJ
    0.26
     telecom
    0.26
    äl
    0.25
    iano
    0.24
     telegram
    0.24
    纺ç»ĩ
    0.24
     Telecom
    0.23
    .getSimpleName
    0.23
    è¾īçħĮ
    0.23
    Activations Density 0.036%

    No Known Activations