© 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. 11818
    Prev
    Next
    INDEX
    Explanations

    type hinting and flow

    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¸įäºī
    -0.08
    xEF
    -0.08
     Permanent
    -0.07
    bsub
    -0.07
    upsi
    -0.07
    /respond
    -0.07
    á»ĩn
    -0.07
    \Security
    -0.07
    permanent
    -0.07
    tempts
    -0.07
    POSITIVE LOGITS
    ours
    0.07
     annotated
    0.07
    å±¥
    0.07
    ickers
    0.06
    ķ
    0.06
    Nullable
    0.06
    asu
    0.06
    ä¿ĬæĿ°
    0.06
    åīįéĢĶ
    0.06
    typed
    0.06
    Activations Density 0.084%

    No Known Activations