© 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. 43023
    Prev
    Next
    INDEX
    Explanations

    foreign

    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
    å¼Ĥ
    -0.39
     foreign
    -0.33
     Foreign
    -0.32
    _foreign
    -0.32
    foreign
    -0.31
    å¤ĸåĽ½
    -0.30
     Ordered
    -0.29
    çķ°
    -0.28
    agon
    -0.27
     synchronous
    -0.27
    POSITIVE LOGITS
    ers
    0.34
    nes
    0.31
    ness
    0.30
    er
    0.30
    ies
    0.28
    ERS
    0.28
    ooting
    0.28
    ersh
    0.28
    ere
    0.27
    cers
    0.27
    Activations Density 0.006%

    No Known Activations