© 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. 33418
    Prev
    Next
    INDEX
    Explanations

    target experiment

    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
    abil
    -0.07
    TRS
    -0.07
    авли
    -0.07
    arser
    -0.07
    stry
    -0.07
    _fill
    -0.07
    å¾·æĸ¯
    -0.07
    çŃī级çļĦ
    -0.06
     desem
    -0.06
     outsiders
    -0.06
    POSITIVE LOGITS
    ç±į
    0.10
    被æĴŀ
    0.09
    åıįåºĶ
    0.09
    iard
    0.08
     reaction
    0.08
    targets
    0.08
     Reaktion
    0.08
    çļĦåıįåºĶ
    0.08
    hosts
    0.08
    /native
    0.08
    Activations Density 0.012%

    No Known Activations