© 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. 25-TRANSCODER-HP
    7. 107685
    Prev
    Next
    INDEX
    Explanations

    calcium

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ded
    -0.30
    eer
    -0.28
     arms
    -0.28
    lat
    -0.26
    alement
    -0.25
    cio
    -0.25
    uce
    -0.25
     heavenly
    -0.24
    ÑijÑĤ
    -0.24
    ìĦĿ
    -0.24
    POSITIVE LOGITS
    ãĤ«ãĥª
    0.27
     molecule
    0.25
    (program
    0.25
     concentrations
    0.25
    åģļå¾Ĺ
    0.25
    åľ¨ä»ĸçļĦ
    0.24
    èĽĽ
    0.24
    apro
    0.24
     mole
    0.24
     programmed
    0.24
    Activations Density 1.144%

    No Known Activations