© 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. 32069
    Prev
    Next
    INDEX
    Explanations

    bolded text

    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
    UnitTest
    -0.07
    ulary
    -0.07
    ़
    -0.07
    é£İäºij
    -0.07
    айÑĤе
    -0.06
    ÑĨ
    -0.06
    HexString
    -0.06
    °
    -0.06
    culate
    -0.06
    amkan
    -0.06
    POSITIVE LOGITS
    ired
    0.08
    ells
    0.08
    yer
    0.08
    elts
    0.08
    lai
    0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    0.07
    缸è¾ħ缸æĪIJ
    0.07
    à¶ļà·Ĭ
    0.07
    .defineProperty
    0.07
    ело
    0.07
    Activations Density 0.006%

    No Known Activations