© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2735
    Prev
    Next
    INDEX
    Explanations

    important point

    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
    sar
    -0.07
    immel
    -0.07
    :str
    -0.07
    ãĤ¯ãĥĪ
    -0.07
    วà¸ģ
    -0.07
     afore
    -0.07
    åħ¶å®ĥ
    -0.06
     ferme
    -0.06
    _GO
    -0.06
    shal
    -0.06
    POSITIVE LOGITS
    ä¸ĩå¤ļåħĥ
    0.07
    éĽ
    0.07
     fascinating
    0.06
    ç¡®å®ŀ
    0.06
     дейÑģÑĤвиÑĤелÑĮно
    0.06
     ################################################################
    0.06
    orong
    0.06
    —and
    0.06
    ç¡®å®ŀæĺ¯
    0.06
    –and
    0.06
    Activations Density 0.041%

    No Known Activations