© 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. 41273
    Prev
    Next
    INDEX
    Explanations

    terminal and command

    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
    毡
    -0.30
     bump
    -0.29
    ections
    -0.28
    ernes
    -0.27
    æĵ
    -0.27
    ichern
    -0.26
    èĬĤ
    -0.25
    orial
    -0.25
    认åIJĮ
    -0.25
    plier
    -0.24
    POSITIVE LOGITS
     prompt
    0.42
    prompt
    0.39
    .prompt
    0.38
     Prompt
    0.37
    _prompt
    0.35
     prompts
    0.35
    Prompt
    0.33
    æıIJ示
    0.32
    (prompt
    0.32
     on
    0.29
    Activations Density 0.017%

    No Known Activations