© 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. 15755
    Prev
    Next
    INDEX
    Explanations

    is this correct?

    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
    转载请注æĺİåĩºå¤Ħ
    -0.07
    _customize
    -0.07
    åıĪä½ķ
    -0.06
    akse
    -0.06
    elaide
    -0.06
    tir
    -0.06
    áŀ¶áŁĨ
    -0.06
    æĥ³å¾ĹåĪ°
    -0.06
    odore
    -0.06
    äºĨè¿Ļ个
    -0.06
    POSITIVE LOGITS
    uns
    0.07
    hein
    0.07
    èĻŀ
    0.07
    ç¥ī
    0.07
    å®Ŀè´Ŀ
    0.06
    æĹ¢åı¯ä»¥
    0.06
    axe
    0.06
    iku
    0.06
    è¿Ľåº¦
    0.06
    unc
    0.06
    Activations Density 0.279%

    No Known Activations