© 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. 24067
    Prev
    Next
    INDEX
    Explanations

    focus

    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
    bon
    -0.27
     inflamm
    -0.26
     brut
    -0.26
    çŃļ
    -0.25
    èIJ¥åķĨ
    -0.25
    _DO
    -0.25
    oval
    -0.25
    Resources
    -0.25
    bow
    -0.24
    严èĤĥ
    -0.24
    POSITIVE LOGITS
    äºĨåįĬ天
    0.31
     principalmente
    0.30
     focusing
    0.28
    çĽ¯çĿĢ
    0.28
     specifically
    0.28
    ercul
    0.27
     mainly
    0.27
    ä¾ĭ
    0.27
    åı¦ä¸ĢåįĬ
    0.26
     only
    0.26
    Activations Density 0.016%

    No Known Activations