© 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. 41985
    Prev
    Next
    INDEX
    Explanations

    variations of "must"

    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
    éĽĨåĽ¢èĤ¡ä»½
    -0.28
     saja
    -0.27
    ipp
    -0.26
     clue
    -0.24
    ipped
    -0.23
     Bernstein
    -0.23
     suited
    -0.23
    ais
    -0.23
    ils
    -0.23
    etal
    -0.23
    POSITIVE LOGITS
    å¿ħé¡»
    1.41
    å¿ħ
    1.37
    Must
    1.30
     must
    1.26
    å¿ħéłĪ
    1.25
    must
    1.24
     Must
    1.23
    å¿ħé¡»è¦ģ
    1.10
     MUST
    1.09
     å¿
    1.09
    Activations Density 0.002%

    No Known Activations