© 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. 20-TRANSCODER-HP
    7. 129953
    Prev
    Next
    INDEX
    Explanations

    Programming/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ateral
    -0.28
    andra
    -0.25
    çĽij
    -0.25
    uli
    -0.25
     constit
    -0.25
     ******************************************************************************↵
    -0.25
    gments
    -0.25
    rolls
    -0.24
    vier
    -0.24
     Dest
    -0.24
    POSITIVE LOGITS
    åıĺéĩı
    0.28
    åĬłä»¥
    0.26
     accurately
    0.25
    (variable
    0.25
    åħ¶æ¬¡æĺ¯
    0.25
    ometown
    0.25
     ironically
    0.24
     wont
    0.24
     inconsist
    0.24
    vas
    0.24
    Activations Density 2.300%

    No Known Activations