© 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. 60732
    Prev
    Next
    INDEX
    Explanations

    tolerance and induction

    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
    ¶
    -0.08
    onal
    -0.08
    åĽŀ缮ãģ®
    -0.07
    rawn
    -0.07
    ToFront
    -0.07
    reiber
    -0.07
     retor
    -0.07
    ierry
    -0.07
    ories
    -0.07
    opping
    -0.07
    POSITIVE LOGITS
    度é«ĺ
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ä½Ļåľ°
    0.09
    patible
    0.08
    度çļĦ
    0.08
    çĻ¾å·Ŀ
    0.08
    å°ıè§ij
    0.08
    ../../../
    0.08
    áĥĵáĥĶ
    0.08
    ±
    0.08
    Activations Density 0.061%

    No Known Activations