© 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. 22004
    Prev
    Next
    INDEX
    Explanations

    miles or km

    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
    ommage
    -0.08
    æ°ijæĶ¿éĥ¨éŨ
    -0.08
    ienz
    -0.08
    ä¸ĢåºĶ
    -0.07
    estet
    -0.07
    æľīæѤ
    -0.07
    estre
    -0.07
     bersangkutan
    -0.07
    _PHASE
    -0.07
     sok
    -0.07
    POSITIVE LOGITS
    æ¼ĶçļĦ
    0.07
    æ¯ĶåĪ©
    0.07
     hare
    0.06
    ç»Ħç»ĩçļĦ
    0.06
    Ùijب
    0.06
    æĿİ家
    0.06
     Acad
    0.06
    circ
    0.06
    astes
    0.06
     pedig
    0.06
    Activations Density 0.004%

    No Known Activations