© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24175
    Prev
    Next
    INDEX
    Explanations

    numerical digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     taxis
    -0.28
     Dallas
    -0.25
    icom
    -0.25
     taps
    -0.24
    edom
    -0.24
    å¸ĪèĮĥ
    -0.24
    ä½İæĪIJæľ¬
    -0.23
    .cap
    -0.23
    Guide
    -0.23
     democrat
    -0.23
    POSITIVE LOGITS
    ä¹ĭäºī
    0.26
    nl
    0.25
    cket
    0.25
    _outer
    0.25
    lette
    0.25
    æ³ķå¾ĭ
    0.24
    лик
    0.24
    LM
    0.24
    åıĮæīĭ
    0.24
    å®´
    0.24
    Activations Density 0.002%

    No Known Activations