© 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. 12-TRANSCODER-HP
    7. 23788
    Prev
    Next
    INDEX
    Explanations

    money

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ascus
    -0.31
    Unit
    -0.27
    onta
    -0.25
    æĮĩ令
    -0.25
    atum
    -0.25
     Meter
    -0.25
    rub
    -0.25
    rang
    -0.24
    meter
    -0.24
     feed
    -0.23
    POSITIVE LOGITS
    ä¸į解
    0.26
     Lump
    0.24
    èµĦæľ¬
    0.23
     Path
    0.23
    ä¸ĢçĶŁ
    0.23
    aurus
    0.23
    asury
    0.23
    æľ¬èº«å°±æĺ¯
    0.22
    _dl
    0.22
     TN
    0.22
    Activations Density 0.003%

    No Known Activations