© 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. 55891
    Prev
    Next
    INDEX
    Explanations

    sign, symbol, representation, reflex

    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
    æĹłéĹ»
    -0.07
    rock
    -0.07
    大åĿĹ
    -0.06
    æĺķ
    -0.06
    ÙĪسÛĮ
    -0.06
    å¹´ç³ķ
    -0.06
    è´Łåİĭ
    -0.06
    以轻
    -0.06
     zer
    -0.06
    oulos
    -0.06
    POSITIVE LOGITS
     détour
    0.08
    代çIJĨæľºæŀĦ
    0.08
    符
    0.08
    符åı·
    0.08
    æłĩè¯Ĩ
    0.08
    æī¿è½½
    0.08
    elic
    0.08
     clues
    0.08
    æĺł
    0.08
    pond
    0.07
    Activations Density 0.016%

    No Known Activations