© 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. 49449
    Prev
    Next
    INDEX
    Explanations

    public services and information

    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
    ingly
    -0.10
    ahui
    -0.09
    ä¸įæĭĶ
    -0.08
    ë§ģ
    -0.08
    ãģ£ãģĵ
    -0.08
    ements
    -0.08
    AndUpdate
    -0.08
    بÙĬÙĩ
    -0.08
    igmat
    -0.07
    å¹³æ¹ĸ
    -0.07
    POSITIVE LOGITS
    -facing
    0.13
    (crate
    0.11
    ity
    0.09
    ized
    0.09
    /private
    0.09
    ologne
    0.09
    ideon
    0.09
    /public
    0.08
    itaire
    0.08
    åł´åIJĪ
    0.08
    Activations Density 0.089%

    No Known Activations