© 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. 29110
    Prev
    Next
    INDEX
    Explanations

    second derivative

    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
    obili
    -0.07
    пÑı
    -0.07
    egah
    -0.07
    oes
    -0.07
    entin
    -0.07
    ambo
    -0.07
    ä¸ĵ家认为
    -0.07
    izzi
    -0.06
    ä¸Ģ带
    -0.06
    ä¸īè¦ģ
    -0.06
    POSITIVE LOGITS
    åħ°è¾¾
    0.07
    usted
    0.07
    менование
    0.07
    åħļæĢ»æĶ¯ä¹¦è®°
    0.07
    客座
    0.07
    ledged
    0.07
     reto
    0.07
    us
    0.07
    ç»Ŀ伦
    0.06
    thon
    0.06
    Activations Density 0.001%

    No Known Activations