© 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. 2582
    Prev
    Next
    INDEX
    Explanations

    wrt

    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
     Roberts
    -0.07
    nf
    -0.07
     //-
    -0.06
    rid
    -0.06
    ä¸Ģ次æĢ§
    -0.06
    ä»İæĪij
    -0.06
    åĪĨåĪ«åľ¨
    -0.06
     Manz
    -0.06
    uci
    -0.06
    æ¶Ī费群ä½ĵ
    -0.06
    POSITIVE LOGITS
    apé
    0.08
    opter
    0.08
    _expression
    0.07
    æIJ
    0.07
    解
    0.07
    ueil
    0.07
    getti
    0.07
    ção
    0.07
     undo
    0.06
    /jav
    0.06
    Activations Density 0.003%

    No Known Activations