© 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. 22874
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    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
    çŁ£
    -0.30
     Quantity
    -0.28
    å°ģ
    -0.27
    壹
    -0.26
     Alto
    -0.26
    综åIJĪ
    -0.26
    uka
    -0.26
     quantity
    -0.26
    ainment
    -0.26
    ä»Ģä¹Īæĺ¯
    -0.25
    POSITIVE LOGITS
    gnore
    0.29
    åľ°å½¢
    0.28
    amma
    0.26
    ORT
    0.26
    ivor
    0.25
    edom
    0.24
    æĿ¼
    0.24
    ç«ij
    0.24
    ::<
    0.24
    isposable
    0.24
    Activations Density 0.003%

    No Known Activations