© 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. 14420
    Prev
    Next
    INDEX
    Explanations

    mental development and emotional growth

    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
     corrup
    -0.09
    常åIJĥ
    -0.08
     intimid
    -0.08
    ä¼ĺåĮĸèIJ¥åķĨçݯå¢ĥ
    -0.08
    adoo
    -0.08
    Ĺı
    -0.08
    ä¸įä½ľä¸º
    -0.08
     assemb
    -0.08
    lada
    -0.08
    çIJĨè®ºåŁºç¡Ģ
    -0.08
    POSITIVE LOGITS
    —
    0.07
    ç»ıéªĮ
    0.07
     sharply
    0.07
    -
    0.07
     organizing
    0.07
    追éĹ®
    0.06
    èĩªè§ī
    0.06
    è´Łè´£ç»Ħç»ĩ
    0.06
     unquestion
    0.06
     erotic
    0.06
    Activations Density 0.106%

    No Known Activations