© 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. 23044
    Prev
    Next
    INDEX
    Explanations

    Ending

    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
    (Json
    -0.27
    è±ĨèħIJ
    -0.27
    å½»åºķ
    -0.27
    enga
    -0.25
     Omn
    -0.24
    è¾¾åĪ°
    -0.24
     pres
    -0.24
    _singular
    -0.24
    ertos
    -0.23
    å²±
    -0.23
    POSITIVE LOGITS
    witch
    0.27
    lfw
    0.25
    æĿĢ
    0.25
    ÑģÑĤÑĢел
    0.24
    Opens
    0.24
     cá»Ń
    0.24
    æĺ¨æĹ¥
    0.24
    å¤ĸæĿ¥
    0.24
     yesterday
    0.24
    bservice
    0.24
    Activations Density 0.002%

    No Known Activations