© 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. 16460
    Prev
    Next
    INDEX
    Explanations

    specific and specialized

    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
    ilde
    -0.08
    åijĹ
    -0.08
    owska
    -0.08
    æĽ´ä¸º
    -0.07
    gnore
    -0.07
    éĺ³åı°ä¸Ĭ
    -0.07
    çĶ©
    -0.07
    lama
    -0.07
    Charsets
    -0.07
     καÏĦά
    -0.07
    POSITIVE LOGITS
    çī¹å®ļ
    0.13
    çī¹å®ļçļĦ
    0.12
    -specific
    0.12
     specific
    0.11
    à¹Ģà¸īà¸ŀาะ
    0.10
    specific
    0.10
    _specific
    0.10
    Specific
    0.09
     Specific
    0.09
    pecific
    0.09
    Activations Density 0.020%

    No Known Activations