© 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. 141141
    Prev
    Next
    INDEX
    Explanations

    Scientific research

    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
    æłĩæĿĨ
    -0.30
    Wik
    -0.27
    å¥ĭ
    -0.27
    æĸĹäºī
    -0.25
     Sher
    -0.25
     Anything
    -0.25
    Century
    -0.25
    忾
    -0.25
     anything
    -0.25
    oulos
    -0.24
    POSITIVE LOGITS
    çľī
    0.30
    nett
    0.29
    _CNTL
    0.28
    eno
    0.25
    joining
    0.25
    *(
    0.25
     Pratt
    0.25
    jian
    0.24
    erno
    0.24
    conciliation
    0.24
    Activations Density 17.295%

    No Known Activations