© 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. 41826
    Prev
    Next
    INDEX
    Explanations

    reading

    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
    orelease
    -0.30
    =obj
    -0.26
    (obj
    -0.25
    ifest
    -0.25
     obj
    -0.25
    æīįè¡Į
    -0.24
    çŁŃæļĤ
    -0.24
     clap
    -0.23
     inline
    -0.23
    duce
    -0.23
    POSITIVE LOGITS
    ç½¢
    0.26
    ESC
    0.24
     satur
    0.24
    homes
    0.24
    é¡
    0.24
    hab
    0.24
    larınız
    0.23
    ema
    0.23
    PU
    0.23
    æĬ½
    0.23
    Activations Density 0.002%

    No Known Activations