© 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. 26378
    Prev
    Next
    INDEX
    Explanations

    input or images

    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
    igm
    -0.07
    olata
    -0.07
    ahoo
    -0.07
    inged
    -0.07
    ема
    -0.07
    ายà¸Ļ
    -0.07
    igg
    -0.07
    çĦ¶å¤§
    -0.07
    ypi
    -0.06
    elos
    -0.06
    POSITIVE LOGITS
    Ñģени
    0.07
    aber
    0.07
    æĸ¯åĿ¦
    0.07
    人以ä¸ĭ
    0.07
    çİĭå°ı
    0.06
    æĭ¯
    0.06
    andle
    0.06
    ãĢij
    0.06
    reek
    0.06
    æ¸Ĭæĺİ
    0.06
    Activations Density 0.001%

    No Known Activations