© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25730
    Prev
    Next
    INDEX
    Explanations

    removal, emission, attenuation, production, coefficient

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è´¦
    -0.07
    常说çļĦ
    -0.06
    æķ¬è¯·æľŁå¾ħ
    -0.06
     appunto
    -0.06
    æľĪç»ıä¸įè°ĥ
    -0.06
    ìĦ±ê¸ī
    -0.06
    cott
    -0.06
    æĬķ稿éĤ®ç®±
    -0.06
    åħĪè¿Ľåħ¸åŀĭ
    -0.06
    ç§ijçłĶå·¥ä½ľ
    -0.06
    POSITIVE LOGITS
     mean
    0.08
    either
    0.07
     trends
    0.07
     analysed
    0.07
    -total
    0.07
    alang
    0.07
    ฯ
    0.07
     uncomp
    0.07
     dece
    0.06
    culated
    0.06
    Activations Density 0.374%

    No Known Activations