© 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. 17886
    Prev
    Next
    INDEX
    Explanations

    OS, transistors, pdf, Assy, blade

    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
    beh
    -0.06
    éĺ¿æ£®
    -0.06
    erte
    -0.06
    ness
    -0.06
    å¦Ĥä¸Ģ
    -0.06
    á»ijng
    -0.06
    éĩijçŁ³
    -0.06
    æĥ³ä¸įåĪ°
    -0.06
    ·
    -0.06
     disjoint
    -0.06
    POSITIVE LOGITS
    åĽ
    0.08
    igny
    0.08
    ä¸ĢçĽ´ä»¥
    0.08
    генÑĤ
    0.08
    Ñĩин
    0.08
    Ĥ¹
    0.07
    ä¸ĢçŃ¹
    0.07
    agak
    0.07
    _RET
    0.07
    @(
    0.07
    Activations Density 0.097%

    No Known Activations