© 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. 63277
    Prev
    Next
    INDEX
    Explanations

    arrows and structure sequences

    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
    umpy
    -0.07
     Troy
    -0.06
    öö
    -0.06
    ByUrl
    -0.06
    erma
    -0.06
    æĪĸåľ¨
    -0.06
    æĪĸä¸İ
    -0.06
    ложений
    -0.06
     *****
    -0.06
    æĪĸ对
    -0.06
    POSITIVE LOGITS
    âĨĴ
    0.11
     âĨĴ
    0.11
     ->
    0.10
    ->
    0.09
    -->
    0.09
     --->
    0.09
    ->$
    0.08
    วà¸Ļ
    0.08
    âĩĴ
    0.08
    ]->
    0.08
    Activations Density 0.040%

    No Known Activations