© 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. 2401
    Prev
    Next
    INDEX
    Explanations

    not necessarily

    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
    大æ¦Ĥæĺ¯
    -0.10
    ilh
    -0.09
    onso
    -0.09
    statt
    -0.09
     probably
    -0.09
    <|box_end|>
    -0.09
    probably
    -0.09
    orida
    -0.09
    assage
    -0.09
    å·®ä¸įå¤ļäºĨ
    -0.09
    POSITIVE LOGITS
    ãģĹãĤĤ
    0.13
    éĿŀè¦ģ
    0.09
     تÙĥÙĪÙĨ
    0.08
    mente
    0.08
    è§ģå¾Ĺ
    0.08
    éĿŀå¾Ĺ
    0.07
    ally
    0.07
    te
    0.06
     ÙĬÙĥÙĪÙĨ
    0.06
    اÙĭ
    0.06
    Activations Density 0.004%

    No Known Activations