© 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. 39487
    Prev
    Next
    INDEX
    Explanations

    prove that

    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
     appunto
    -0.08
     simplement
    -0.08
    究竣
    -0.08
    åĪ°åºķ
    -0.07
     simplesmente
    -0.07
     magari
    -0.07
    åħ¸èĹı
    -0.07
    eneric
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
     ÑıкобÑĭ
    -0.07
    POSITIVE LOGITS
     preliminary
    0.09
    Lemma
    0.09
    åĪĿæŃ¥
    0.09
     Lemma
    0.08
     lemma
    0.08
     prelimin
    0.08
    alin
    0.08
    alu
    0.08
    éĵºåŀ«
    0.07
    æĢ§è´¨
    0.07
    Activations Density 0.038%

    No Known Activations