© 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. 28588
    Prev
    Next
    INDEX
    Explanations

    measuring concentration

    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
    itage
    -0.08
    ory
    -0.08
    -fashioned
    -0.08
    áticos
    -0.07
    åħ¢åħ¢ä¸ļä¸ļ
    -0.07
    身临åħ¶å¢ĥ
    -0.07
    ะà¸Ļัà¹īà¸Ļ
    -0.07
    INGTON
    -0.07
    atically
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    POSITIVE LOGITS
    ément
    0.10
    plx
    0.10
    åĴĮä½ľçĶ¨
    0.09
    esz
    0.09
    igna
    0.09
    epas
    0.09
    -badge
    0.09
    ezza
    0.09
    nect
    0.08
    encies
    0.08
    Activations Density 0.025%

    No Known Activations