© 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. 22475
    Prev
    Next
    INDEX
    Explanations

    repeat

    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
    ï¼ļ%
    -0.28
    åªĴä½ĵ
    -0.26
    è¯ģå®ŀ
    -0.25
    人éĢī
    -0.24
     statistics
    -0.23
    åªĴé«Ķ
    -0.23
    åı¯ä¾Ľ
    -0.23
     láºŃp
    -0.23
    åħ±è¯Ĩ
    -0.23
    :?
    -0.23
    POSITIVE LOGITS
    	rect
    0.28
    arine
    0.28
    å±
    0.28
    uum
    0.27
    idders
    0.27
    _PWR
    0.25
    ump
    0.25
    ãģ£ãģ±
    0.25
    UMP
    0.24
     plur
    0.24
    Activations Density 0.004%

    No Known Activations