© 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. 16932
    Prev
    Next
    INDEX
    Explanations

    byte int long

    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
    elin
    -0.09
    ONS
    -0.08
    ä¸įæ±Ĥ
    -0.08
    enin
    -0.08
    ouse
    -0.08
    urin
    -0.08
    erin
    -0.08
    ennie
    -0.07
    ä¸Ģåıij
    -0.07
    olin
    -0.07
    POSITIVE LOGITS
    udio
    0.07
    DSL
    0.06
    ¶
    0.06
    udah
    0.06
    çĶ±åİŁåijĬ
    0.06
    并å®ĮæĪIJ
    0.06
    èĢ¦
    0.06
    å¤ļä¸ĢçĤ¹
    0.06
    nya
    0.06
     Offen
    0.06
    Activations Density 0.003%

    No Known Activations