© 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. 58385
    Prev
    Next
    INDEX
    Explanations

    forms of words, variations, or copies

    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
     cushion
    -0.07
    ç²¾åĪ¶
    -0.06
    æĮ½
    -0.06
    sume
    -0.06
    åħ¬éģĵ
    -0.06
     nit
    -0.06
    æ¸ħæ°Ķ
    -0.06
    æĶ¿åįıåī¯ä¸»å¸Ń
    -0.06
    åıĮèī²
    -0.06
     Ashton
    -0.06
    POSITIVE LOGITS
    移ä½į
    0.10
    SHIFT
    0.09
     shifted
    0.09
    -away
    0.08
    _forms
    0.08
     relocated
    0.08
    veri
    0.08
    -shift
    0.08
    acie
    0.08
    _locations
    0.08
    Activations Density 0.007%

    No Known Activations