© 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. 47112
    Prev
    Next
    INDEX
    Explanations

    usually followed by verbs or clauses

    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
    jenigen
    -0.14
    णà¥Ģ
    -0.10
    assage
    -0.10
    ossible
    -0.10
    Ùģاض
    -0.09
    Ùī
    -0.09
    ãĤĪãģĨãģª
    -0.09
    urah
    -0.09
    nowled
    -0.09
    rim
    -0.09
    POSITIVE LOGITS
    ãģĦãĤĭ
    0.11
    Ø©
    0.11
    s
    0.09
    ات
    0.08
    er
    0.08
    lijk
    0.07
    и
    0.07
    o
    0.07
    ä»ĸæĬĬ
    0.07
    amment
    0.06
    Activations Density 0.030%

    No Known Activations