© 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. 15312
    Prev
    Next
    INDEX
    Explanations

    ions and chemical compounds

    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
     beis
    -0.08
    ray
    -0.07
    æľīçĶ¨çļĦ
    -0.07
    èİ«åIJįçļĦ
    -0.06
    被åĪ«äºº
    -0.06
    çĽ¸ä¼ł
    -0.06
    amble
    -0.06
    æĶ¯æĮģä¸İ
    -0.06
    éģIJ
    -0.06
    ä¸İæĶ¯æĮģ
    -0.06
    POSITIVE LOGITS
    estro
    0.08
    å°Ĩåħ¶
    0.08
    ihn
    0.07
    使åħ¶
    0.07
     antid
    0.07
    arges
    0.07
    ä¸İä¹ĭ
    0.07
    对åħ¶
    0.07
    .Destroy
    0.07
    _chunks
    0.07
    Activations Density 0.046%

    No Known Activations