© 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. 33138
    Prev
    Next
    INDEX
    Explanations

    still lacking or not yet

    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
    çļĦä¸Ģ个
    -0.07
    igon
    -0.07
    çĦ¦
    -0.07
    æľīåħ³äºİ
    -0.07
    èĻ½çĦ¶æĺ¯
    -0.06
     gorge
    -0.06
     sot
    -0.06
    èĮ«èĮ«
    -0.06
    .ib
    -0.06
    ä¸įåĽł
    -0.06
    POSITIVE LOGITS
     altrett
    0.07
    canf
    0.07
    çĽħ
    0.07
    èĿł
    0.07
    ¹Ħ
    0.07
     CascadeType
    0.07
    èħ¹é»ij
    0.07
    {@
    0.07
    OLTIP
    0.07
    (PC
    0.07
    Activations Density 0.377%

    No Known Activations