© 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. 33-TRANSCODER-HP
    7. 53637
    Prev
    Next
    INDEX
    Explanations

    medic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    -0.29
    ithub
    -0.27
    ter
    -0.27
    åķ¡
    -0.27
    é£İ
    -0.25
    ther
    -0.25
    icipant
    -0.25
     mission
    -0.24
    tlement
    -0.24
     well
    -0.24
    POSITIVE LOGITS
    éĽªèĬ±
    0.30
    cly
    0.30
    hol
    0.30
    board
    0.29
    -board
    0.29
    arel
    0.27
     Painter
    0.27
    år
    0.27
     allowNull
    0.27
    -cl
    0.26
    Activations Density 0.010%

    No Known Activations