© 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. 3507
    Prev
    Next
    INDEX
    Explanations

    book titles and authors

    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¸ĭåIJĮ
    -0.08
    alik
    -0.08
    ãĥ©ãģ®
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    eca
    -0.07
    ecas
    -0.06
    ÙĦاغ
    -0.06
    æľ¬çīĪ
    -0.06
    sov
    -0.06
    产ä¸ļç»ĵæŀĦè°ĥæķ´
    -0.06
    POSITIVE LOGITS
     aka
    0.10
    aka
    0.08
    åıĪåIJį
    0.08
    åİŁæĺ¯
    0.07
    çĶ±åIJĦ
    0.07
    /code
    0.06
    ä¹ŁçĶ±
    0.06
    fatt
    0.06
    åĬłæĭ¿å¤§
    0.06
    åı¯ä»¥çĶ±
    0.06
    Activations Density 0.388%

    No Known Activations