© 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. 41738
    Prev
    Next
    INDEX
    Explanations

    variable assignment or placeholder

    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
    aint
    -0.08
    unto
    -0.07
    inti
    -0.07
    BigInt
    -0.07
    ([^
    -0.07
    WARDS
    -0.07
    ban
    -0.07
    illet
    -0.06
    isen
    -0.06
    æĪŁ
    -0.06
    POSITIVE LOGITS
    ç»®
    0.08
    ipper
    0.07
    issor
    0.07
    ä¸įèµ·
    0.07
    ropolis
    0.07
    ä¾ĭå¦Ĥ
    0.07
    诸å¦Ĥ
    0.07
    ÑģÑĤаÑı
    0.07
    æł©
    0.07
    ropol
    0.07
    Activations Density 0.035%

    No Known Activations