© 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. 129864
    Prev
    Next
    INDEX
    Explanations

    environment

    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
     Ih
    -0.29
     let
    -0.27
    ØŃÙĪ
    -0.25
    ây
    -0.25
    än
    -0.25
     happen
    -0.24
    æł¸åĩĨ
    -0.24
    ved
    -0.24
    illis
    -0.24
    ëĶ©
    -0.23
    POSITIVE LOGITS
     amph
    0.30
    ä¸īæĿ¡
    0.26
    mui
    0.25
    çĶ±ä¸ŃåĽ½
    0.24
    _MUT
    0.24
    æľĶ
    0.24
    ferred
    0.24
    ATAB
    0.24
    poon
    0.24
    jours
    0.24
    Activations Density 8.296%

    No Known Activations