© 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. 46902
    Prev
    Next
    INDEX
    Explanations

    considering next steps

    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
    umpa
    -0.07
    ophe
    -0.06
    çĶ¨å¿ĥåİ»
    -0.06
    æĮĸæİĺåħ¬åı¸
    -0.06
    æIJģ
    -0.06
    让çݩ家
    -0.06
    æĮīä¸Ģä¸ĭ
    -0.06
    å¢ħ
    -0.06
    ol
    -0.06
    æ·¡æ·¡
    -0.06
    POSITIVE LOGITS
    ãĤĴæ¤ľè¨İ
    0.09
    æĥ³çŁ¥éģĵ
    0.09
    è·ĥè·ĥ
    0.09
     prospective
    0.08
     deciding
    0.08
    åĨ³å®ļæĺ¯åIJ¦
    0.08
    åħ¨éĿ¢äºĨ解
    0.08
    ä¿¡æģ¯æŁ¥è¯¢
    0.08
    -options
    0.07
     purchasing
    0.07
    Activations Density 0.485%

    No Known Activations