© 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. 46397
    Prev
    Next
    INDEX
    Explanations

    suffix -ive/-ity/-ent

    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
    尼奥
    -0.08
    à¬Ľ
    -0.07
    оди
    -0.07
     pro
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
     fred
    -0.07
    ffre
    -0.07
     comp
    -0.07
    vro
    -0.07
    IRON
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĽ¾
    0.07
    arana
    0.07
    orz
    0.07
    arden
    0.07
    Ì
    0.07
    oward
    0.07
    folio
    0.06
    orne
    0.06
    enfant
    0.06
    èque
    0.06
    Activations Density 0.101%

    No Known Activations