© 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. 30-TRANSCODER-HP
    7. 96521
    Prev
    Next
    INDEX
    Explanations

    нов

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivor
    -0.31
     Standing
    -0.28
    icol
    -0.28
     makeStyles
    -0.28
    arend
    -0.27
     standing
    -0.27
    éĻIJ
    -0.26
    èĢ¸
    -0.26
    Standing
    -0.26
    æŃ»èĢħ
    -0.24
    POSITIVE LOGITS
     prot
    0.39
    prot
    0.34
     prote
    0.33
    atin
    0.30
     prop
    0.29
    /hooks
    0.29
    OMB
    0.28
     charge
    0.28
    hee
    0.28
    ling
    0.27
    Activations Density 1.015%

    No Known Activations