© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13987
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    isson
    -0.09
    ittal
    -0.07
    resp
    -0.07
    æŁ¥çľĭ详æĥħ
    -0.07
    æĪĸå°ij
    -0.07
    arrass
    -0.07
    adf
    -0.07
    åħ´åįİ
    -0.07
    éķ¿èĻ¹
    -0.07
    ewe
    -0.07
    POSITIVE LOGITS
     thereby
    0.10
    åħ¶å¯¹
    0.09
     deren
    0.09
    åħ¶ä¸İ
    0.09
    çĶ±æѤ
    0.09
     therein
    0.09
    åħ¶åľ¨
    0.09
    以æѤæĿ¥
    0.08
     their
    0.08
    对åħ¶è¿Ľè¡Į
    0.08
    Activations Density 0.283%

    No Known Activations