© 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. 3792
    Prev
    Next
    INDEX
    Explanations

    temperature points and states

    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
    åĢ¦
    -0.08
    _der
    -0.07
    esan
    -0.07
    eret
    -0.07
    åı¸æ³ķæīĢ
    -0.07
    æ²¹éĩı
    -0.07
    hed
    -0.07
     distances
    -0.07
    /goto
    -0.07
    ç´¯çļĦ
    -0.07
    POSITIVE LOGITS
     Celsius
    0.08
    åĽ½æŃĮ
    0.08
    æµij身
    0.08
    临çķĮ
    0.08
    沸èħ¾
    0.07
    çĨĶçĤ¹
    0.07
     Fahrenheit
    0.07
     spontan
    0.07
     spontaneously
    0.07
    avana
    0.07
    Activations Density 0.004%

    No Known Activations