© 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. 11816
    Prev
    Next
    INDEX
    Explanations

    number 2 followed by period

    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
     Alonso
    -0.06
    R
    -0.06
    neau
    -0.06
    au
    -0.06
    .,
    -0.05
    gy
    -0.05
    ney
    -0.05
    ardini
    -0.05
    åĪĻæľī
    -0.05
    éĹŃ
    -0.05
    POSITIVE LOGITS
    uas
    0.09
    irut
    0.08
    à¸ĸู
    0.08
    trias
    0.08
    _HINT
    0.08
    ÏĢη
    0.08
    iras
    0.08
    _SCHED
    0.08
    TPL
    0.08
    habit
    0.08
    Activations Density 0.172%

    No Known Activations