© 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. 16354
    Prev
    Next
    INDEX
    Explanations

    disclaimer/notes, also

    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
    以æѤ
    -0.07
    ...
    -0.07
    âĢ¦
    -0.07
    å¹¶è¿Ľ
    -0.07
    oint
    -0.07
    âĢ¦âĢ¦
    -0.06
     THEN
    -0.06
    /articles
    -0.06
    mlin
    -0.06
    è¿Ļéĥ¨åĪĨ
    -0.06
    POSITIVE LOGITS
    ussion
    0.09
    arena
    0.08
    áĥ¦
    0.08
    kee
    0.08
    å°½éĩıéĢīæĭ©
    0.07
    chg
    0.07
     remb
    0.07
    lef
    0.07
    /ext
    0.07
    landa
    0.07
    Activations Density 0.074%

    No Known Activations