© 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. 41007
    Prev
    Next
    INDEX
    Explanations

    requirements

    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
    ίοÏħ
    -0.08
    åĭĩå¾Ģ缴åīį
    -0.08
    ection
    -0.08
    ebr
    -0.08
    OVO
    -0.08
    ä½ľçĶ¨æĺ¯
    -0.08
    Ī
    -0.08
    oare
    -0.08
    cid
    -0.07
    sports
    -0.07
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.09
    ëĮĢë¡ľ
    0.09
    åĴĮ建议
    0.09
    ful
    0.08
    fulness
    0.08
     ìĤ¬íķŃ
    0.08
    ter
    0.08
    Ķ
    0.07
    semb
    0.07
    åĴĮè¦ģæ±Ĥ
    0.07
    Activations Density 0.041%

    No Known Activations