© 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. 19948
    Prev
    Next
    INDEX
    Explanations

    indices and positions

    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
    ry
    -0.09
    ness
    -0.08
    onia
    -0.07
    /he
    -0.07
    rz
    -0.07
    shire
    -0.07
    çĺ¾
    -0.06
    byte
    -0.06
    ↵
    -0.06
    /left
    -0.06
    POSITIVE LOGITS
    好ä¹ħ
    0.08
    lech
    0.08
    ValuePair
    0.08
    ä¸Ĭè¯ģ
    0.08
    WithError
    0.08
    aÅŁ
    0.08
     corrispond
    0.08
    inally
    0.07
    USAGE
    0.07
    LETE
    0.07
    Activations Density 0.010%

    No Known Activations