© 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. 16240
    Prev
    Next
    INDEX
    Explanations

    original, og, it, kala

    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
    μο
    -0.07
     perk
    -0.07
    fetch
    -0.07
    çĶ¨çĶµ
    -0.06
    _nc
    -0.06
    åĪļ
    -0.06
    æ²Ł
    -0.06
    lec
    -0.06
    éĩĩ
    -0.06
    ä¸į缺
    -0.06
    POSITIVE LOGITS
     اÙĦأصÙĦÙĬ
    0.09
     original
    0.09
    åİŁæľīçļĦ
    0.09
     originalmente
    0.08
    åİŁ
    0.08
    otec
    0.08
    original
    0.08
    ç²®
    0.08
    åİŁæľī
    0.08
    åİŁæľ¬çļĦ
    0.08
    Activations Density 0.223%

    No Known Activations