© 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. 63193
    Prev
    Next
    INDEX
    Explanations

    `[@B` references

    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
    asti
    -0.07
    lose
    -0.06
    éªı
    -0.06
    olec
    -0.06
    Styled
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    æľ´
    -0.06
    trice
    -0.06
    åIJĪä½ľçļĦ
    -0.06
    ulat
    -0.06
    POSITIVE LOGITS
    ungan
    0.08
    izz
    0.08
    erein
    0.07
     remet
    0.07
    erei
    0.07
    äºĶ级
    0.07
    elman
    0.07
    IZZ
    0.07
    iesz
    0.07
    inting
    0.06
    Activations Density 0.001%

    No Known Activations