© 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. 43964
    Prev
    Next
    INDEX
    Explanations

    hole cooling nanotube Drag layer sequence Eraser

    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
     ÑģмÑĭ
    -0.07
    æŃ
    -0.07
     valg
    -0.07
     Pessoa
    -0.07
    omotor
    -0.07
    èIJ½èĬ±
    -0.06
    è´±
    -0.06
    æĹ
    -0.06
    æĹłè®ºæĺ¯åľ¨
    -0.06
    ache
    -0.06
    POSITIVE LOGITS
    åĬłéĢŁ
    0.08
    æĸ¯çī¹
    0.08
     casinos
    0.08
    并åıij
    0.08
     accelerated
    0.07
    ãĥĩãĤ¤
    0.07
    åŃĺç»Ń
    0.07
    åѤå¯Ĥ
    0.07
    ç»Ń
    0.07
    å°¾éĥ¨
    0.07
    Activations Density 0.002%

    No Known Activations