© 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. 107746
    Prev
    Next
    INDEX
    Explanations

    code/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
    IRO
    -0.30
    dep
    -0.25
    abh
    -0.24
    è´´
    -0.23
    пÑĭ
    -0.23
    ัà¸Ļ
    -0.23
    пиÑĤ
    -0.23
    ä¹ŁæĹłæ³ķ
    -0.23
     dep
    -0.23
    enh
    -0.23
    POSITIVE LOGITS
    itage
    0.26
    æĺ¯ä¸ª
    0.26
    ButtonDown
    0.26
    <?,
    0.25
    lectic
    0.25
    nine
    0.25
     fingertips
    0.24
    å¾Īéĩįè¦ģçļĦ
    0.24
    éªħ
    0.24
    é£İæ³¢
    0.24
    Activations Density 2.186%

    No Known Activations