© 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. 43228
    Prev
    Next
    INDEX
    Explanations

    text descriptions

    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
    host
    -0.30
     Host
    -0.29
     host
    -0.28
    Host
    -0.28
    ipers
    -0.27
    Lean
    -0.26
    ucc
    -0.26
    _host
    -0.25
    ä½ıæĪ¿
    -0.24
    ucas
    -0.24
    POSITIVE LOGITS
     ãĥĪãĥ©ãĥĥãĤ¯
    0.29
     ilaç
    0.28
    åIJĪ
    0.27
    鼷
    0.27
     drug
    0.25
    æłĩçļĦ
    0.25
     Gim
    0.25
     Pry
    0.24
    ç±³å°Ķ
    0.24
     sal
    0.24
    Activations Density 0.002%

    No Known Activations