© 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. 16696
    Prev
    Next
    INDEX
    Explanations

    Ask HN, ary wing

    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
    Äĥn
    -0.09
     meantime
    -0.07
    Ư
    -0.07
    acid
    -0.07
    quera
    -0.06
    atta
    -0.06
    izzano
    -0.06
    EAU
    -0.06
     McKay
    -0.06
     Turnbull
    -0.06
    POSITIVE LOGITS
    rical
    0.08
    udir
    0.07
    ä¸īéŨ
    0.07
    ÑıÑħ
    0.07
    chio
    0.07
    /slider
    0.06
    ä¸įèĢģ
    0.06
    onné
    0.06
    agerie
    0.06
    rams
    0.06
    Activations Density 0.044%

    No Known Activations