© 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. 41268
    Prev
    Next
    INDEX
    Explanations

    unrelated word followed by specific words

    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
    oner
    -0.11
     ÐĴÑģÑĤÑĢе
    -0.10
     ÐŁÐ¾Ñģко
    -0.09
    oned
    -0.09
    ighton
    -0.09
    रà¥įव
    -0.09
     Сооб
    -0.09
     Grunde
    -0.09
    izen
    -0.08
    onas
    -0.08
    POSITIVE LOGITS
    ness
    0.12
    ç´§è¦ģ
    0.10
    ä¹İ
    0.10
    ä¹İåħ¶
    0.10
    s
    0.10
    äºİä¸ĸ
    0.08
    sworth
    0.07
    سÙĦÙĪب
    0.07
     chặt
    0.07
    äºİæѤ
    0.07
    Activations Density 0.001%

    No Known Activations