© 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. 23221
    Prev
    Next
    INDEX
    Explanations

    Course

    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
    Ste
    -0.29
    æį¢
    -0.26
     Formats
    -0.25
    æµİ
    -0.25
    upp
    -0.25
    èĥĦ
    -0.25
    Plate
    -0.24
    arriv
    -0.24
    çİij
    -0.24
     Steph
    -0.24
    POSITIVE LOGITS
    alis
    0.26
     concurrent
    0.26
    &page
    0.25
    ç³»åĪĹæ´»åĬ¨
    0.25
    hon
    0.24
    趣åij³
    0.24
    pta
    0.23
    оÑĨен
    0.23
     retros
    0.23
    æĶ»åĬ¿
    0.23
    Activations Density 0.001%

    No Known Activations