© 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. 12406
    Prev
    Next
    INDEX
    Explanations

    list items and code delimiters

    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
    uj
    -0.07
    /
    -0.07
    -0.06
    heit
    -0.06
     at
    -0.06
    ho
    -0.06
    ith
    -0.06
    iek
    -0.06
    vs
    -0.06
    å¦Ĥçİī
    -0.06
    POSITIVE LOGITS
    è·ĥè·ĥ欲è¯ķ
    0.10
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    åĭ¤åĭ¤æģ³æģ³
    0.09
    åħ¨å¿ĥåħ¨æĦı
    0.09
    apult
    0.09
    åįģä¸ĢäºĶ
    0.09
    èĢ³çĨŁèĥ½è¯¦
    0.09
    缸è¾ħ缸æĪIJ
    0.08
    ¡°
    0.08
    äºĭåįĬåĬŁåĢį
    0.08
    Activations Density 0.131%

    No Known Activations