© 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. 42861
    Prev
    Next
    INDEX
    Explanations

    scheduled, rights, use

    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
    æĸ¯åŁº
    -0.10
    леÑĨ
    -0.08
    Clinton
    -0.07
    inho
    -0.07
    çŃı
    -0.07
    insi
    -0.07
    _BLE
    -0.07
    culp
    -0.07
     efficac
    -0.07
    posted
    -0.07
    POSITIVE LOGITS
    è±
    0.07
    owie
    0.07
    ç®ĹäºĨ
    0.07
    çķ
    0.07
    Ĩ
    0.07
    otra
    0.07
    otomy
    0.07
    akan
    0.06
    çĻ¾ç§ij
    0.06
    elve
    0.06
    Activations Density 0.117%

    No Known Activations