© 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. 7840
    Prev
    Next
    INDEX
    Explanations

    online startup and practice swims

    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
    frog
    -0.07
     famously
    -0.07
    ¿IJ
    -0.06
    onz
    -0.06
    alis
    -0.06
    ndo
    -0.06
     mors
    -0.06
    好åĥı
    -0.06
    æĹ©åľ¨
    -0.06
    æīįæľīäºĨ
    -0.06
    POSITIVE LOGITS
     likely
    0.08
    æĦıåij³èijĹ
    0.08
    å°ıå±±
    0.08
    @d
    0.08
    Lik
    0.08
    æ¹ĥ
    0.08
    ollah
    0.08
    åIJįæĢĿ
    0.07
    为æıIJé«ĺ
    0.07
     implique
    0.07
    Activations Density 0.041%

    No Known Activations