© 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. 46382
    Prev
    Next
    INDEX
    Explanations

    company or product names

    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
    ĽĦ
    -0.09
    .ua
    -0.08
    ÑĦон
    -0.08
    eor
    -0.08
    èIJį
    -0.07
    agine
    -0.07
    å°±æĺ¯æĥ³
    -0.07
    彼岸
    -0.07
    æĥ³å¾ĹåĪ°
    -0.07
    éĽªå³°
    -0.07
    POSITIVE LOGITS
    西
    0.07
    åĪĴ
    0.06
    oci
    0.06
    åįĹ
    0.06
    arring
    0.06
     {*}
    0.06
    å®ļ
    0.06
    çĶŁè¾°
    0.06
    åŃĺæ¡£
    0.06
     NW
    0.06
    Activations Density 0.486%

    No Known Activations