© 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. 20876
    Prev
    Next
    INDEX
    Explanations

    sorting by length or weight

    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
     rô
    -0.07
    æľ¬ç«ł
    -0.07
    roles
    -0.07
    æľ¬èĬĤ
    -0.07
    åħ¬åħ¬
    -0.07
    oghi
    -0.07
    _closure
    -0.07
    éĹŃéŨ
    -0.07
    馨
    -0.07
    ä»ħä»£è¡¨ä½ľèĢħ
    -0.07
    POSITIVE LOGITS
    ä¼ĺåħĪ
    0.10
    priority
    0.10
    riority
    0.10
     priority
    0.09
    ä¼ĺåħĪèĢĥèĻij
    0.09
    åĦªåħĪ
    0.08
     Priority
    0.08
    ä¼ĺåħĪ级
    0.08
     priorities
    0.08
    plevel
    0.08
    Activations Density 0.024%

    No Known Activations