© 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. 57383
    Prev
    Next
    INDEX
    Explanations

    legality

    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
    (Module
    -0.28
    ç´§
    -0.26
     criterion
    -0.25
    ÑĤиÑĢов
    -0.24
    被æīĵ
    -0.24
    surface
    -0.24
     reasoned
    -0.23
    .Command
    -0.23
    .surface
    -0.23
    Surface
    -0.23
    POSITIVE LOGITS
     legal
    1.37
    æ³ķå¾ĭ
    1.16
     Legal
    1.12
    legal
    1.11
    Legal
    1.08
     legally
    1.06
     legality
    1.04
    æ³ķå¾ĭæ³ķè§Ħ
    1.04
    æ³ķå¾ĭè§Ħå®ļ
    0.97
     laws
    0.94
    Activations Density 0.050%

    No Known Activations