© 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. 23435
    Prev
    Next
    INDEX
    Explanations

    Place names

    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
    çIJĨæĢ§
    -0.28
    APSHOT
    -0.27
    ogl
    -0.27
     yard
    -0.27
    é£İå°ļ
    -0.26
    checksum
    -0.26
    æĮĩå¼ķ
    -0.26
    umi
    -0.25
    ehler
    -0.25
    etter
    -0.24
    POSITIVE LOGITS
     nep
    0.25
    åĬĽè¿ĺæĺ¯
    0.25
    åĿĢ
    0.25
    ;line
    0.25
    åĪ©çī©
    0.25
     kicked
    0.24
    å¾Īéķ¿
    0.24
     newState
    0.24
     humanoid
    0.23
     ÄIJình
    0.23
    Activations Density 0.001%

    No Known Activations