© 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. 23192
    Prev
    Next
    INDEX
    Explanations

    Building interiors/exteriors

    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
    çݯå¢ĥä¸Ń
    -0.28
    iations
    -0.26
     ambiguity
    -0.26
    æ°¸ä¹ħ
    -0.25
     ambient
    -0.25
    bul
    -0.24
    ogne
    -0.24
     addressing
    -0.24
    ç¼ĩ
    -0.24
    æł¡åıĭ
    -0.23
    POSITIVE LOGITS
    colo
    0.27
    æŁ¥çľĭæĽ´å¤ļ
    0.27
    zc
    0.26
     Exist
    0.26
     Exists
    0.26
    åģĩ
    0.25
    isposable
    0.25
     exist
    0.25
    ä¹ĸ
    0.25
     cor
    0.25
    Activations Density 0.003%

    No Known Activations