© 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. 10541
    Prev
    Next
    INDEX
    Explanations

    "It" followed by verbs/pronouns

    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
    ules
    -0.07
    м
    -0.07
    atsu
    -0.07
    ic
    -0.07
    incs
    -0.06
    мÑı
    -0.06
     matlab
    -0.06
    ijnen
    -0.06
    emberg
    -0.06
    éĵ¶å±±
    -0.06
    POSITIVE LOGITS
    orable
    0.07
    ìłĦìĿĢ
    0.07
    ðŁĺĢ
    0.07
    ìłĦìĹIJ
    0.07
    dig
    0.07
    oke
    0.07
    ä¸īåı£
    0.07
    aug
    0.07
    欢è¿İ访éĹ®
    0.07
    ç«ĭåį³ä¸ĭè½½
    0.06
    Activations Density 0.004%

    No Known Activations