© 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. 8929
    Prev
    Next
    INDEX
    Explanations

    technically/supposed/intended/ideal

    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
    ä¸ĬæīĢ
    -0.08
    æĢ»åı°
    -0.07
    Ðģ
    -0.07
    anea
    -0.06
    å«£
    -0.06
    eto
    -0.06
    wat
    -0.06
    opa
    -0.06
    hor
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    POSITIVE LOGITS
    ä¸įè¿ĩåľ¨
    0.10
    ä½ĨçĶ±äºİ
    0.10
     theoretically
    0.10
     ideally
    0.09
    çIJĨ论ä¸Ĭ
    0.09
    ä½Ĩçİ°åľ¨
    0.09
    ä¸įè¿ĩ
    0.09
    ä½Ĩåľ¨
    0.08
    ä½ĨåĽłä¸º
    0.08
    ä½Ĩèĩ³å°ij
    0.08
    Activations Density 0.045%

    No Known Activations