© 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. 64545
    Prev
    Next
    INDEX
    Explanations

    disproportionately weighted or proportional

    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
     добÑĢа
    -0.08
    å¾ĺ
    -0.08
     ساÙĦÙħ
    -0.08
    ä¿ĿæĮģ稳å®ļ
    -0.08
    ä¸ļåĬ¡èĮĥåĽ´
    -0.08
    ä¿ĿæĮģé«ĺ度
    -0.08
    è¶³å¤Ł
    -0.07
    chetta
    -0.07
    èĢĺ
    -0.07
     komple
    -0.07
    POSITIVE LOGITS
     weighting
    0.16
     weighted
    0.15
    -weight
    0.14
     weights
    0.13
    æĿĥéĩį
    0.13
    åĬłæĿĥ
    0.13
     disproportionately
    0.13
     unequal
    0.12
    weighted
    0.12
     proportional
    0.11
    Activations Density 0.080%

    No Known Activations