© 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. 142202
    Prev
    Next
    INDEX
    Explanations

    period

    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
    è¿Ļ两个
    -0.30
    æķĪçİĩ
    -0.28
    piler
    -0.25
    ä¸¤å¼ł
    -0.25
    è¿Ļ两
    -0.25
    åĪĨæ³Į
    -0.25
    éĢł
    -0.25
     scram
    -0.25
    inem
    -0.24
    åĩĿ
    -0.24
    POSITIVE LOGITS
    çĻ¾å¼º
    0.27
    åħ¨éĿ¢
    0.26
     above
    0.25
    >'.
    0.25
    bd
    0.24
    樾
    0.24
    _clk
    0.24
    é©°æı´
    0.24
    _buffer
    0.23
    semble
    0.23
    Activations Density 1.121%

    No Known Activations