© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44819
    Prev
    Next
    INDEX
    Explanations

    entity names and measurements

    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
    å¢ĥ
    -0.07
    æ¯Ķä¾ĭ为
    -0.07
    æīĢ以çİ°åľ¨
    -0.07
    ç¼
    -0.06
    æĥħåĨµè¯´æĺİ
    -0.06
     Lowell
    -0.06
    èĶ
    -0.06
    å¹´é¾Ħè¦ģæ±Ĥ
    -0.06
    æĥħåĨµåĪĨæŀIJ
    -0.06
    ç¼ĺæķħ
    -0.06
    POSITIVE LOGITS
     measured
    0.10
    Measured
    0.09
    çħ¦
    0.08
     измеÑĢÑı
    0.08
    —the
    0.07
    æ®ĥ
    0.07
    å®ŀéĻħ
    0.07
    apura
    0.07
     communicated
    0.07
     measurable
    0.07
    Activations Density 0.058%

    No Known Activations