© 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. 107995
    Prev
    Next
    INDEX
    Explanations

    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
     dist
    -0.27
    ignet
    -0.26
     niezb
    -0.26
    Initializer
    -0.25
    upp
    -0.25
    caret
    -0.25
    åįłæľī
    -0.25
    igh
    -0.25
    æķ´æ²»
    -0.25
    综åIJĪ
    -0.24
    POSITIVE LOGITS
    acted
    0.32
    pit
    0.27
    olygon
    0.26
    æijĩäºĨæijĩ头
    0.25
    ery
    0.25
    lrt
    0.25
    éģĵå¾·
    0.24
    (QL
    0.24
     Crow
    0.24
    amm
    0.24
    Activations Density 37.888%

    No Known Activations