© 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
    2. Qwen3-4B
    3. 32-TRANSCODER-HP
    4. 41565
    Prev
    Next
    INDEX
    Explanations

    Names of people or things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elig
    -0.26
    çļĦæĸ¹åIJij
    -0.26
    okie
    -0.26
    ijo
    -0.25
    elige
    -0.24
    habi
    -0.24
    ede
    -0.23
    idue
    -0.23
     punct
    -0.23
     punctuation
    -0.23
    POSITIVE LOGITS
     Partial
    0.27
     partial
    0.27
    çĸ¡
    0.26
    æ°´å¹³
    0.25
    Partial
    0.25
    æįŁ
    0.25
    screen
    0.25
     гоÑĢ
    0.25
     traff
    0.25
     Ali
    0.25
    Activations Density 0.001%

    No Known Activations