© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61785
    Prev
    Next
    INDEX
    Explanations

    account, 8, k

    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
    orra
    -0.07
     glac
    -0.06
    æ¶īå«Į
    -0.06
    omotive
    -0.06
    elte
    -0.06
    çݯæ¯Ķ
    -0.06
    åīįèĢħ
    -0.06
    plode
    -0.05
    oriously
    -0.05
    canvas
    -0.05
    POSITIVE LOGITS
    ashi
    0.08
    çļĦç»ıèIJ¥çIJĨ念
    0.08
    пи
    0.08
    深深
    0.07
    cci
    0.07
    ţe
    0.07
    çī§ç¾Ĭ
    0.07
    gó
    0.07
    tvr
    0.07
    ativi
    0.07
    Activations Density 0.010%

    No Known Activations