© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33171
    Prev
    Next
    INDEX
    Explanations

    buzz on, flyer above, corruption in, yes come, matchmaking it, entertain all, parts first, international shipping

    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
    onsel
    -0.09
    éĢĤäºİ
    -0.08
    轻轻æĿ¾
    -0.08
    å¹´èİ·
    -0.08
    è¿Ł
    -0.07
    ’)
    -0.07
    estruc
    -0.07
    oload
    -0.07
    æĪijåį´
    -0.07
    å®ŀå¤Ħ
    -0.07
    POSITIVE LOGITS
    è¯¾æľ¬
    0.07
    æķ¢
    0.07
    ÙIJ
    0.07
    żÄħ
    0.06
    annels
    0.06
    ibd
    0.06
    è¿Ļä¸ĢåĪĩ
    0.06
    <-
    0.06
    otten
    0.06
     vibe
    0.06
    Activations Density 0.016%

    No Known Activations