© 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. 20435
    Prev
    Next
    INDEX
    Explanations

    numbers around percentages, counts, or citations

    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
    KY
    -0.08
    olla
    -0.07
    è§
    -0.07
    onio
    -0.07
     respects
    -0.07
     fucks
    -0.06
    Attribute
    -0.06
     attribute
    -0.06
     Spy
    -0.06
    spy
    -0.06
    POSITIVE LOGITS
    è¯ħ
    0.08
    ANJI
    0.07
    embra
    0.07
    itung
    0.07
    æĬ¤åıij
    0.07
     stok
    0.07
     Finalmente
    0.07
    .omg
    0.07
     uncon
    0.07
    hack
    0.07
    Activations Density 0.007%

    No Known Activations