© 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. 142059
    Prev
    Next
    INDEX
    Explanations

    turn

    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
    /from
    -0.27
     coerc
    -0.27
    ä¸ĩè¾Ĩ
    -0.25
    PIN
    -0.24
    约æĿŁ
    -0.23
    minster
    -0.23
     Driving
    -0.23
     sworn
    -0.23
    åľŁ
    -0.23
    æ·±å±Ĥ次
    -0.23
    POSITIVE LOGITS
    antly
    0.28
    çĴ¨
    0.26
    sed
    0.26
    _AA
    0.25
    /current
    0.25
    ANTE
    0.24
    apas
    0.23
    ibal
    0.23
     shade
    0.23
     practice
    0.23
    Activations Density 22.221%

    No Known Activations