© 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. 23429
    Prev
    Next
    INDEX
    Explanations

    success rate

    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¸įæ¸ħ
    -0.09
    æ·±å¤ĦçļĦ
    -0.09
     ulang
    -0.09
    avance
    -0.09
    aksim
    -0.08
    araf
    -0.08
    etat
    -0.08
    upro
    -0.08
    ssue
    -0.08
    egen
    -0.08
    POSITIVE LOGITS
    s
    0.09
    ä¸İåIJ¦
    0.09
    -looking
    0.09
    åĴĮä¸į足
    0.08
    fully
    0.08
    /error
    0.07
    es
    0.07
    OrFail
    0.07
    full
    0.07
    ably
    0.07
    Activations Density 0.041%

    No Known Activations