© 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. 28793
    Prev
    Next
    INDEX
    Explanations

    angles and arithmetic expressions

    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
    δÏĮ
    -0.07
    å½ķ
    -0.06
    ODO
    -0.06
     Sha
    -0.06
    شط
    -0.06
    IZ
    -0.06
    ç½ĹåĪĹ
    -0.06
    kid
    -0.06
     around
    -0.06
    around
    -0.06
    POSITIVE LOGITS
    ADVERTISEMENT
    0.07
    åľ°çĵľ
    0.07
    ayout
    0.07
    该è¡Į
    0.07
    rador
    0.07
    rada
    0.07
    å¾ĭå·±
    0.07
    Einst
    0.07
    Äĥn
    0.06
    apache
    0.06
    Activations Density 0.014%

    No Known Activations