© 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. 44004
    Prev
    Next
    INDEX
    Explanations

    fields and institutions

    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
    cpy
    -0.10
    麹
    -0.09
    weiler
    -0.08
    以赴
    -0.08
    _ipv
    -0.08
    -lite
    -0.08
    éĻ¤æѤ
    -0.08
    ষà§į
    -0.08
    çĻ¾å§ĵç½ij
    -0.07
    abetic
    -0.07
    POSITIVE LOGITS
    xxx
    0.07
     XXX
    0.07
    XXX
    0.06
    åIJĦ级
    0.06
    æŁIJæŁIJ
    0.06
    å°Ķçī¹
    0.06
    _symbols
    0.06
     or
    0.06
     Pal
    0.06
     xxx
    0.06
    Activations Density 0.335%

    No Known Activations