© 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. 17829
    Prev
    Next
    INDEX
    Explanations

    only with/is/the

    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
    odz
    -0.08
    åıªèĥ½çĶ¨
    -0.07
    å°±ç®ĹäºĨ
    -0.07
    æģ©æĸ¯
    -0.07
     super
    -0.07
    urf
    -0.07
    åįİéĺ³
    -0.07
    acha
    -0.07
    æĻ´å¤©
    -0.07
    大红
    -0.07
    POSITIVE LOGITS
    åī©ä¸ĭ
    0.09
    åī©ä¸ĭçļĦ
    0.08
    åħ¶é¤ĺ
    0.08
    rint
    0.08
    ä¸įèī¯
    0.07
    åķıé¡Įãģ¯
    0.07
    å½ĵæĪij们
    0.07
    èĻij
    0.07
    OTO
    0.07
     restantes
    0.07
    Activations Density 0.076%

    No Known Activations