© 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. 43019
    Prev
    Next
    INDEX
    Explanations

    student

    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
     College
    -0.44
    college
    -0.40
     college
    -0.40
    大åѦ
    -0.40
     Colleg
    -0.38
    College
    -0.38
     colleges
    -0.37
     university
    -0.36
     universities
    -0.36
     University
    -0.35
    POSITIVE LOGITS
    _party
    0.30
    enant
    0.29
    æĸ°å¼Ģ
    0.27
    abyte
    0.27
    人群
    0.25
     hitting
    0.25
     entering
    0.25
    çĦ¦
    0.24
    ATUS
    0.24
     working
    0.24
    Activations Density 0.005%

    No Known Activations