© 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. 17413
    Prev
    Next
    INDEX
    Explanations

    citations and numbers

    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
    对ä¸ŃåĽ½
    -0.07
    åį³ä»¥
    -0.06
    å°ĨæѤ
    -0.06
    ãĥĻãĥ¼ãĤ¹
    -0.06
    anc
    -0.06
    æ¢Ĩ
    -0.06
    obe
    -0.06
    feld
    -0.06
    çĶ²éª¨
    -0.06
    обоÑĢоÑĤ
    -0.06
    POSITIVE LOGITS
    社
    0.08
    enius
    0.07
    ieÅĦ
    0.07
    iesta
    0.07
    ienti
    0.07
    交大
    0.07
    arbeiten
    0.07
    ((&
    0.07
    uger
    0.07
    nesia
    0.07
    Activations Density 0.092%

    No Known Activations