© 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. 23-TRANSCODER-HP
    7. 24638
    Prev
    Next
    INDEX
    Explanations

    uch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .gov
    -0.28
     delt
    -0.26
    æľªæĿ¥
    -0.26
    ä¸įå¼Ģ
    -0.25
    irected
    -0.25
     Edited
    -0.24
    pii
    -0.23
     Fil
    -0.23
     sooner
    -0.23
     parten
    -0.23
    POSITIVE LOGITS
    åĻ¨
    0.28
    å½¹
    0.27
    弩
    0.26
    illery
    0.25
    üt
    0.24
    achu
    0.24
     Commands
    0.24
     setColor
    0.23
    _BUFF
    0.23
     addUser
    0.23
    Activations Density 0.002%

    No Known Activations