© 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. 25345
    Prev
    Next
    INDEX
    Explanations

    sentence endings

    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
    éĿĴå±±
    -0.08
    ç´
    -0.08
    nd
    -0.07
    软
    -0.07
    wig
    -0.07
    çĦ¶åIJİ
    -0.07
    íĥľ
    -0.07
    anh
    -0.06
    çī¹
    -0.06
    conn
    -0.06
    POSITIVE LOGITS
    人ä¹ĭ
    0.08
    osz
    0.08
    ụ
    0.08
     hyper
    0.07
    ÙĪÙĦÙĬÙĨ
    0.07
    oss
    0.07
    æŶéľĢ
    0.07
    å¦Ĥä½ķåĪ©çĶ¨
    0.07
    çĻ¾åº¦äºij
    0.07
    hyper
    0.07
    Activations Density 0.008%

    No Known Activations