© 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. 4308
    Prev
    Next
    INDEX
    Explanations

    special characters or malformed content

    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
    pira
    -0.09
    èĩªå¾Ĺ
    -0.08
    æĤį
    -0.08
    reck
    -0.08
    ä¸įæŃ»
    -0.07
    è¦ģä¹Ī
    -0.07
    arrer
    -0.07
    åĬłåħ³æ³¨
    -0.07
    ansen
    -0.07
    oppable
    -0.07
    POSITIVE LOGITS
     already
    0.08
     malformed
    0.08
     вообÑīе
    0.08
     overlapping
    0.07
     too
    0.07
    è¿ĩ大
    0.07
     outright
    0.07
    è¿ĩå°ı
    0.07
    å·²ç»ıå¾Ī
    0.07
    too
    0.07
    Activations Density 0.014%

    No Known Activations