© 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. 18997
    Prev
    Next
    INDEX
    Explanations

    concreteItaniumcondominiumMurphyGX

    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
    iaux
    -0.07
    entrant
    -0.07
    ãģ«éĻIJ
    -0.07
    âľħ
    -0.06
    utura
    -0.06
    иÑĤоÑĢ
    -0.06
    å¿ħçŃĶ
    -0.06
    åĴĮæĻºæħ§
    -0.06
    ĵĺ
    -0.06
    åľ¨ç»Ļ
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.12
     ÑıкобÑĭ
    0.09
    æĪĸåħ¶å®ĥ
    0.09
    unlikely
    0.08
    éĤ£æł·çļĦ
    0.08
    æĪĸåħ¶ä»ĸ
    0.08
     would
    0.08
    ridge
    0.08
     wäre
    0.07
     skulle
    0.07
    Activations Density 0.087%

    No Known Activations