© 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. 23617
    Prev
    Next
    INDEX
    Explanations

    numbers followed by `x` or digits

    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
    çŁ¥åħ¶
    -0.07
    æŃ»
    -0.07
    ë£Į를
    -0.07
    orte
    -0.07
    å½ĵåħ¶
    -0.06
    ance
    -0.06
    æµ·æ£ł
    -0.06
    使å®ĥ
    -0.06
     herm
    -0.06
    éĻĭ
    -0.06
    POSITIVE LOGITS
    ReadStream
    0.09
    èĺĭ
    0.08
    ikir
    0.08
    imary
    0.08
    ummings
    0.08
     Narrow
    0.07
    ÙĨÙĩا
    0.07
    åĻĮ
    0.07
    éĹ¯åħ³
    0.07
    artz
    0.07
    Activations Density 0.017%

    No Known Activations