© 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. 27-TRANSCODER-HP
    7. 57061
    Prev
    Next
    INDEX
    Explanations

    Law

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¢Ĺç²Ĵ
    -0.28
    个人
    -0.27
    zew
    -0.27
    pyx
    -0.26
    峪
    -0.26
     oversh
    -0.25
    iron
    -0.24
    å·¡èĪª
    -0.24
    åĢĭ人
    -0.24
    ä¿Ŀé²ľ
    -0.24
    POSITIVE LOGITS
     legality
    0.31
    æ³ķå¾ĭæ³ķè§Ħ
    0.30
     legal
    0.30
     legally
    0.28
    æ³ķå¾ĭ
    0.28
     legislation
    0.28
     Legal
    0.27
    ters
    0.27
    logue
    0.26
     Dependencies
    0.26
    Activations Density 0.003%

    No Known Activations