© 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. 43601
    Prev
    Next
    INDEX
    Explanations

    punctuation and therefore

    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
    OnClick
    -0.07
    .stub
    -0.07
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.07
    ParameterValue
    -0.07
    chwitz
    -0.07
    Ïĩή
    -0.07
    ä¸Ģå®ļéĩıçļĦ
    -0.07
    Charset
    -0.07
    _CAST
    -0.07
    Ø°
    -0.07
    POSITIVE LOGITS
    æķħ
    0.11
    æķħæѤ
    0.10
    åĽłæѤ
    0.09
     therefore
    0.08
    æīĢ以
    0.08
    èĢĮä¸įæĺ¯
    0.08
    æķħèĢĮ
    0.08
     hence
    0.07
    æķħåIJį
    0.07
     Therefore
    0.07
    Activations Density 0.059%

    No Known Activations