© 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. 22358
    Prev
    Next
    INDEX
    Explanations

    cooking

    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
    ä¼ı
    -0.30
     pilgr
    -0.28
    igner
    -0.27
    è§Ħ
    -0.26
    .jet
    -0.25
    über
    -0.25
    é¢ĦèѦ
    -0.24
    ç¼ĸ
    -0.24
    ler
    -0.24
    HeaderValue
    -0.24
    POSITIVE LOGITS
    .TryParse
    0.33
    POCH
    0.26
    ÃŃc
    0.26
    Ñģко
    0.26
    ç½ij讯
    0.24
    xac
    0.24
     Maths
    0.24
    ewire
    0.24
    æ±Ľ
    0.24
     bunk
    0.23
    Activations Density 0.001%

    No Known Activations