© 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. 28886
    Prev
    Next
    INDEX
    Explanations

    breakdown or degradation

    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
    Moment
    -0.08
    èĵĸ
    -0.07
    issy
    -0.07
    mano
    -0.07
    å¢
    -0.07
    mux
    -0.07
    agno
    -0.06
    icali
    -0.06
     abduction
    -0.06
     moment
    -0.06
    POSITIVE LOGITS
    åĪĨ解
    0.15
    æĭĨ解
    0.14
    éĩĬæĶ¾åĩº
    0.12
     decomposition
    0.11
     breakdown
    0.11
    解ä½ĵ
    0.11
    æĭĨ
    0.11
    æĭĨå¼Ģ
    0.11
     decom
    0.11
     Decom
    0.11
    Activations Density 0.049%

    No Known Activations