© 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. 63176
    Prev
    Next
    INDEX
    Explanations

    presumably

    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
    å°½æĥħçļĦ
    -0.09
    ième
    -0.08
    hoven
    -0.08
    bauer
    -0.08
    zugeben
    -0.08
    eenth
    -0.08
    etlen
    -0.08
     admittedly
    -0.08
     reportedly
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    POSITIVE LOGITS
    umably
    0.10
    å·²ä¹ħçļĦ
    0.07
    mente
    0.07
    erweise
    0.07
    ä½Ĩä¸įéĻIJäºİ
    0.07
    ãģĹãĤĤ
    0.07
    ä»İéĤ£
    0.06
    CISION
    0.06
     nhiên
    0.06
    çĤľ
    0.06
    Activations Density 0.026%

    No Known Activations