© 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. 21869
    Prev
    Next
    INDEX
    Explanations

    named or located

    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§ģ她
    -0.08
    á»ij
    -0.08
    leben
    -0.08
    è¨Ģéģĵ
    -0.07
    amani
    -0.07
    anko
    -0.07
    _NT
    -0.07
    åįĩæľ¬
    -0.07
    ä¸įæ¯Ķ
    -0.07
    accomp
    -0.07
    POSITIVE LOGITS
    妥妥
    0.09
    åIJįåŃĹåı«
    0.07
    åIJįåī¯åħ¶å®ŀçļĦ
    0.07
    å±ŀ
    0.07
     Communications
    0.07
    大家
    0.07
     nicknamed
    0.07
    åIJįåī¯åħ¶å®ŀ
    0.07
    quis
    0.06
    对åºĶçļĦ
    0.06
    Activations Density 0.047%

    No Known Activations