© 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. 43100
    Prev
    Next
    INDEX
    Explanations

    drive

    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
    leting
    -0.27
     spons
    -0.27
    pret
    -0.27
    éĢ¢
    -0.26
    /xml
    -0.25
    段
    -0.25
    issuer
    -0.25
    $xml
    -0.25
    ensing
    -0.24
    åı°ä¸Ĭ
    -0.24
    POSITIVE LOGITS
     drive
    0.39
    驱åĬ¨
    0.39
     drives
    0.38
    drive
    0.36
    -drive
    0.33
     driving
    0.32
    éĿ¢ç§¯çº¦
    0.32
     drove
    0.30
    驱
    0.29
    éĿ¢ç§¯
    0.29
    Activations Density 0.000%

    No Known Activations