© 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. 16814
    Prev
    Next
    INDEX
    Explanations

    also, thereof, pass through

    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
    åĪĻæľī
    -0.07
    apur
    -0.07
    apel
    -0.07
     Ris
    -0.07
    decl
    -0.07
     Lotus
    -0.06
    æ¡ĵ
    -0.06
    .sy
    -0.06
    ç«ŁçĦ¶æĺ¯
    -0.06
    ppen
    -0.06
    POSITIVE LOGITS
    èĩªçĦ¶ä¹Ł
    0.10
    èıģèĭ±
    0.08
    æį²
    0.07
    arc
    0.07
    å¿ħçĦ¶
    0.07
     thereof
    0.07
    ãģķãĤĤ
    0.07
    æĽ´ä½ķåĨµ
    0.07
    çļĦä¸Ģå®ļ
    0.07
    ynt
    0.07
    Activations Density 0.010%

    No Known Activations