© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 56862
    Prev
    Next
    INDEX
    Explanations

    maximizing or minimizing values

    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
    igna
    -0.07
    jou
    -0.07
    ourd
    -0.07
    ardia
    -0.06
    kana
    -0.06
    iche
    -0.06
    ique
    -0.06
    豪
    -0.06
    fld
    -0.06
    .flow
    -0.06
    POSITIVE LOGITS
    å°½åı¯èĥ½
    0.12
    å°½åı¯èĥ½åľ°
    0.10
    å°½éĩı
    0.09
    è¶Ĭä½İ
    0.09
    ìĪĺë¡Ŀ
    0.09
     minimizing
    0.08
    æľĢ大åĮĸ
    0.08
    è¶Ĭ好
    0.08
    å°½éĩıåĩıå°ij
    0.08
    åºĶå°½éĩı
    0.08
    Activations Density 0.003%

    No Known Activations