© 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. 10203
    Prev
    Next
    INDEX
    Explanations

    important ideas

    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
    ils
    -0.08
    æĨ¬
    -0.08
    que
    -0.08
     Fortun
    -0.07
    eman
    -0.07
    orna
    -0.07
    STS
    -0.07
    orni
    -0.07
    quem
    -0.07
    åı¯æĤ²
    -0.07
    POSITIVE LOGITS
    <<<<<<<
    0.07
    åİ
    0.07
    æĥķ
    0.07
    łĢ
    0.07
    èĪİ
    0.07
    éĻįèIJ½
    0.07
    ython
    0.07
    Ta
    0.06
    iser
    0.06
    æİ¥ä¸ĭ
    0.06
    Activations Density 0.232%

    No Known Activations