© 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. 32-TRANSCODER-HP
    7. 42083
    Prev
    Next
    INDEX
    Explanations

    code/computer language

    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
    ha
    -0.28
    orsche
    -0.27
    eca
    -0.26
    acus
    -0.26
    hr
    -0.25
     Spir
    -0.25
    hol
    -0.25
    aha
    -0.25
    acom
    -0.25
    ære
    -0.24
    POSITIVE LOGITS
    ÑĤок
    0.29
    RAM
    0.27
    tx
    0.26
    town
    0.26
    åı©
    0.26
     dip
    0.26
    Bell
    0.26
    ond
    0.25
    è¯
    0.25
    å¯Ŀ
    0.25
    Activations Density 0.005%

    No Known Activations