© 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. 51374
    Prev
    Next
    INDEX
    Explanations

    list items delimited by colon

    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
    udas
    -0.07
     Kl
    -0.07
    涯
    -0.07
     Famili
    -0.06
    _TRANSL
    -0.06
    áĥ¬
    -0.06
    ocere
    -0.06
    æIJŃ
    -0.06
     Rock
    -0.06
    itre
    -0.06
    POSITIVE LOGITS
    unner
    0.07
    &action
    0.07
    kiye
    0.07
    guide
    0.07
    iske
    0.07
    ToMany
    0.06
    åħ¶èģĮ
    0.06
    imb
    0.06
    SUP
    0.06
    ذاÙĥ
    0.06
    Activations Density 0.001%

    No Known Activations