© 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. 23280
    Prev
    Next
    INDEX
    Explanations

    Underwater

    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
    å¿łå®ŀ
    -0.30
    pname
    -0.27
    ennes
    -0.27
    æīĢåľ¨
    -0.26
     electronic
    -0.26
     Colour
    -0.26
    èĥ½åģļåĪ°
    -0.25
     contents
    -0.25
    å®ļçĤ¹
    -0.25
    alue
    -0.25
    POSITIVE LOGITS
    imeter
    0.27
    æ·º
    0.25
    ninger
    0.25
    imeters
    0.25
    æµħ
    0.25
    heard
    0.25
    .cv
    0.24
    lease
    0.24
    sap
    0.24
     VOID
    0.24
    Activations Density 0.001%

    No Known Activations