© 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. 23259
    Prev
    Next
    INDEX
    Explanations

    decimal places

    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
    baugh
    -0.08
    ucid
    -0.08
    butt
    -0.08
    æĽ´çĶŁ
    -0.08
     envis
    -0.07
    oyal
    -0.07
    è°ģä¹Ł
    -0.07
    egos
    -0.07
    éb
    -0.07
    ég
    -0.07
    POSITIVE LOGITS
    红æ¢ħ
    0.07
     precision
    0.07
    ä½įæķ°
    0.07
    èĪį
    0.06
     صØŃ
    0.06
    å¿ħ须注æĺİ
    0.06
    ä¸Ģåħ±æľī
    0.06
    æĬĢæľ¯è§ĦèĮĥ
    0.06
    ilde
    0.06
     doe
    0.06
    Activations Density 0.004%

    No Known Activations