© 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. 31397
    Prev
    Next
    INDEX
    Explanations

    temperature and gases

    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
    宽带
    -0.08
    亲
    -0.08
    CASCADE
    -0.08
    otka
    -0.08
    级çļĦ
    -0.08
    亲亲
    -0.07
    级
    -0.07
    æľ¬çº§
    -0.07
    親
    -0.07
    çĶµå·¥
    -0.07
    POSITIVE LOGITS
     temperature
    0.11
     gases
    0.11
    æ°Ķä½ĵçļĦ
    0.10
    temperature
    0.10
    æ°Ķä½ĵ
    0.10
    å¯ĨéĹŃ
    0.10
    容积
    0.09
     Temperature
    0.09
     gas
    0.09
     temperatures
    0.09
    Activations Density 0.003%

    No Known Activations