© 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. 58738
    Prev
    Next
    INDEX
    Explanations

    agenda item or issue

    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
    otka
    -0.08
    ulp
    -0.08
    åħ¶ä¸ŃæľĢ
    -0.07
    pson
    -0.07
    _initializer
    -0.07
    åħ¶çī¹å¾ģ
    -0.07
    åħ¶èº«
    -0.07
    ä»İåħ¶
    -0.07
    VL
    -0.07
    åħ¶ä¸ī
    -0.07
    POSITIVE LOGITS
     بÙĪدÙĨ
    0.08
    onian
    0.07
    ļ
    0.07
    ä¾ł
    0.07
    ellis
    0.06
     aleg
    0.06
    Ñı
    0.06
    z
    0.06
    леÑĢ
    0.06
    andle
    0.06
    Activations Density 0.470%

    No Known Activations