© 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. 19256
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
     pandang
    -0.08
    &T
    -0.08
    /&
    -0.08
    &C
    -0.07
    &R
    -0.07
    çħľ
    -0.07
    aruh
    -0.07
    ÐľÐķÐĿ
    -0.07
    imir
    -0.07
    &M
    -0.07
    POSITIVE LOGITS
    iecz
    0.06
    ason
    0.06
    taus
    0.06
    以ä¸ĭç®Ģ称
    0.06
     DÃŃaz
    0.06
    opp
    0.06
    ased
    0.06
    ilate
    0.06
    žel
    0.06
    Ùģاع
    0.06
    Activations Density 0.614%

    No Known Activations