© 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. 24468
    Prev
    Next
    INDEX
    Explanations

    date and value 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
    çĽĸä¸ĸ
    -0.08
    举
    -0.07
    å°ıè®°èĢħ
    -0.07
    pector
    -0.07
    REAT
    -0.07
    chien
    -0.07
    folios
    -0.07
    asso
    -0.06
    ä¸įæĢķ
    -0.06
    ä¸Ĭå¸ĤåIJİ
    -0.06
    POSITIVE LOGITS
    _STANDARD
    0.09
    æłĩåĩĨ
    0.09
     assumed
    0.09
     standard
    0.08
    æłĩåĩĨçļĦ
    0.08
    standard
    0.08
    åħ¬è®¤çļĦ
    0.08
    æłĩåĩĨ为
    0.08
    çļĦæłĩåĩĨ
    0.08
    常çĶ¨çļĦ
    0.08
    Activations Density 0.007%

    No Known Activations