© 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. 129628
    Prev
    Next
    INDEX
    Explanations

    as

    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
    ç´§åĩij
    -0.29
    驳
    -0.29
    ivery
    -0.28
    /MIT
    -0.25
    åĹ
    -0.25
     versa
    -0.24
    ------+------+
    -0.24
     medium
    -0.24
     cảnh
    -0.24
    rolley
    -0.24
    POSITIVE LOGITS
    (stdin
    0.28
    人为
    0.26
    angi
    0.26
    cov
    0.25
     BUG
    0.25
    ETS
    0.25
     reproduction
    0.24
    æĹıèĩªæ²»åİ¿
    0.24
    ä¸įéĶĪ
    0.24
    å®ī
    0.24
    Activations Density 11.185%

    No Known Activations