© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2377
    Prev
    Next
    INDEX
    Explanations

    different types of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鳡
    -0.23
    åĩĢåĪ©æ¶¦
    -0.22
     simplest
    -0.22
    ä»ĬåIJİ
    -0.21
    Debugger
    -0.21
     ever
    -0.21
     something
    -0.21
    æĪĸèĢħ说
    -0.21
     hindsight
    -0.21
    ä¸İåħ¶ä»ĸ
    -0.20
    POSITIVE LOGITS
    ially
    0.46
    iating
    0.43
    iates
    0.41
    ials
    0.40
     kinds
    0.39
    ç±»åŀĭçļĦ
    0.38
    iable
    0.37
     types
    0.35
    iability
    0.35
    -sized
    0.34
    Activations Density 0.050%

    No Known Activations