© 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. 31-TRANSCODER-HP
    7. 18911
    Prev
    Next
    INDEX
    Explanations

    arm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icons
    -0.27
    æ°¸éģł
    -0.26
    astr
    -0.25
    urous
    -0.25
    جÙĦ
    -0.25
     cons
    -0.24
     Husband
    -0.24
    erais
    -0.24
     strr
    -0.24
    ä¼ļéķ¿
    -0.24
    POSITIVE LOGITS
    arm
    0.30
    ape
    0.29
    侧éĿ¢
    0.29
    /arm
    0.27
     shoulder
    0.26
    .arm
    0.26
     arm
    0.25
    annels
    0.24
    arms
    0.24
    èĤ©èĨĢ
    0.24
    Activations Density 0.007%

    No Known Activations