© 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. 19508
    Prev
    Next
    INDEX
    Explanations

    comes

    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
    èĵ¼
    -0.30
    ç»ĻäºĪäºĨ
    -0.26
    _BACK
    -0.26
    Appear
    -0.26
    è¡Ķ
    -0.25
     gave
    -0.25
     appearances
    -0.25
     prosec
    -0.24
    StringValue
    -0.24
    æŁ´
    -0.24
    POSITIVE LOGITS
    éĸĵ
    0.28
     поб
    0.28
     direct
    0.24
    fact
    0.24
    çIJ²
    0.23
    currentColor
    0.23
    ÃĹ↵↵
    0.23
    éĹ´
    0.23
     validity
    0.23
    缴æİ¥
    0.23
    Activations Density 0.015%

    No Known Activations