© 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. 23-TRANSCODER-HP
    7. 25145
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     other
    -0.41
    åħ¶ä»ĸçļĦ
    -0.41
    åħ¶ä½Ļ
    -0.32
    other
    -0.30
     others
    -0.30
    eri
    -0.28
    åħ¶ä»ĸ
    -0.28
     Other
    -0.28
    åħ¶å®ĥ
    -0.28
    Other
    -0.27
    POSITIVE LOGITS
    avenport
    0.25
     Languages
    0.25
    icle
    0.24
    æĸĩç«ł
    0.24
    ament
    0.24
     illustrated
    0.23
    åı¬
    0.23
    /games
    0.23
    ich
    0.23
    amble
    0.23
    Activations Density 0.020%

    No Known Activations