© 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. 43895
    Prev
    Next
    INDEX
    Explanations

    arts and entertainment media

    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
    è¶Ĭ
    -0.07
    riding
    -0.07
    管çIJĨå±Ģ
    -0.06
     Syst
    -0.06
    Ń
    -0.06
    ç½ijåıĭä¸Ĭä¼ł
    -0.06
     unconditional
    -0.06
    ouble
    -0.06
    è°ģéĥ½
    -0.06
     mild
    -0.06
    POSITIVE LOGITS
    çŃīå¤ļç§įå½¢å¼ı
    0.09
    çŃīé¢ĨåŁŁçļĦ
    0.08
     prose
    0.08
    çŃīé¢ĨåŁŁ
    0.08
    lish
    0.08
    åıĬéħįå¥Ĺ
    0.08
     spoken
    0.08
    illage
    0.08
    çŃīå½¢å¼ı
    0.08
    çŃīåħ¶ä»ĸ
    0.08
    Activations Density 0.185%

    No Known Activations