© 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. 130304
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    åĢ¼å¾Ĺ
    -0.28
    就被
    -0.27
    è¿ĺ羣æĺ¯
    -0.25
    履约
    -0.25
    mot
    -0.24
    .opensource
    -0.24
     Catalonia
    -0.24
    zÄĻ
    -0.23
    å²Ľå±¿
    -0.23
    utow
    -0.23
    POSITIVE LOGITS
    åħļæĶ¿
    0.29
     traps
    0.28
    .templates
    0.26
     poil
    0.24
    èĥ¸åīį
    0.24
     Mim
    0.23
    ndl
    0.23
    Ä°R
    0.23
    ween
    0.23
    賦
    0.23
    Activations Density 17.927%

    No Known Activations