© 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. 42821
    Prev
    Next
    INDEX
    Explanations

    (

    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
    ""↵
    -0.28
    缸è¯Ĩ
    -0.28
    .Disclaimer
    -0.28
    æĸ°éĹ»åıijå¸ĥ
    -0.28
    OnUiThread
    -0.25
    bnb
    -0.24
    ileaks
    -0.24
     ::↵
    -0.24
    hetto
    -0.24
    "';↵
    -0.24
    POSITIVE LOGITS
     ),
    0.32
     )↵↵
    0.30
    **)
    0.30
    _)
    0.29
    )(
    0.29
    )ï¼Į
    0.29
    ?)
    0.29
    .)
    0.29
    请
    0.29
    ï¼īï¼Į
    0.28
    Activations Density 0.004%

    No Known Activations