© 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. 22625
    Prev
    Next
    INDEX
    Explanations

    Fold

    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
     pen
    -0.29
    åľ°ä¸ĭ
    -0.26
    ç¬Ķ
    -0.25
    uvre
    -0.25
    unter
    -0.25
    oked
    -0.25
    -fat
    -0.24
     coils
    -0.24
    æįĤ
    -0.24
    奶
    -0.24
    POSITIVE LOGITS
    为空
    0.36
    Appe
    0.26
    é£ĵ
    0.25
    碰æĴŀ
    0.24
    çıŃéķ¿
    0.24
    æľºåĬ¨
    0.24
     mour
    0.23
    email
    0.23
    ãĤĴãģ¤ãģij
    0.23
    æ°©
    0.23
    Activations Density 0.001%

    No Known Activations