© 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. 30497
    Prev
    Next
    INDEX
    Explanations

    .pl, .m, .C, .s, .d, .b, .de, .p

    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
    je
    -0.07
    ASIL
    -0.07
    identally
    -0.07
    INGTON
    -0.06
    _idxs
    -0.06
    æ½¢
    -0.06
    prene
    -0.06
    ICIENT
    -0.06
    \"
    -0.06
    asant
    -0.06
    POSITIVE LOGITS
    æľ¬æĸĩçĶ±
    0.09
    ,ev
    0.08
    æľ¬åŃIJ
    0.08
     **>>
    0.08
    大æ³ķ
    0.08
    lrt
    0.08
    yss
    0.08
    pv
    0.08
    erb
    0.07
    otime
    0.07
    Activations Density 0.450%

    No Known Activations