© 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. 14-TRANSCODER-HP
    7. 40855
    Prev
    Next
    INDEX
    Explanations

    \

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umas
    -0.27
    å°±æĺ¯è¿Ļæł·
    -0.27
    uges
    -0.26
    bidden
    -0.26
     talked
    -0.25
     pó
    -0.25
    bic
    -0.25
    çłĶ究表æĺİ
    -0.24
     tud
    -0.24
    ailer
    -0.24
    POSITIVE LOGITS
    olute
    0.28
    Directive
    0.27
    .native
    0.25
    еÑĤе
    0.25
    åIJĮèĥŀ
    0.24
    ä¾Ķ
    0.24
    ç¼ĸåĪ¶
    0.24
    antage
    0.23
     favour
    0.23
     egg
    0.23
    Activations Density 5.541%

    No Known Activations