© 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. 9148
    Prev
    Next
    INDEX
    Explanations

    legal and copyright issues

    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
    brit
    -0.27
     tái
    -0.27
    对æ¯Ķ
    -0.25
    æ´»åĬ¨çİ°åľº
    -0.25
    -eng
    -0.25
    ượng
    -0.25
    بشر
    -0.24
    iders
    -0.24
    人æīįéĺŁä¼į
    -0.24
     Nail
    -0.24
    POSITIVE LOGITS
     legal
    0.44
     legally
    0.39
     copyright
    0.37
     Legal
    0.35
    legal
    0.35
    ä¸ĵåĪ©
    0.35
    Legal
    0.34
     copyrighted
    0.33
    æ³ķå¾ĭ
    0.32
    èijĹä½ľæĿĥ
    0.32
    Activations Density 0.002%

    No Known Activations