© 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. 64262
    Prev
    Next
    INDEX
    Explanations

    code snippets with type declarations

    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
    uar
    -0.07
    对åı£
    -0.07
    issons
    -0.07
    emplo
    -0.07
    å±Ĥ
    -0.06
    warts
    -0.06
    岩
    -0.06
    åijĬ
    -0.06
     Äijá»ĵn
    -0.06
    ä¸ĢåĪĩ
    -0.06
    POSITIVE LOGITS
    à´Łà´¿
    0.08
     input
    0.07
    åħ¨è·¯æ®µ
    0.07
     accordingly
    0.07
    cesi
    0.07
     StringTokenizer
    0.07
    ogat
    0.07
    inded
    0.07
    å°¾
    0.07
    éĹ·
    0.07
    Activations Density 0.021%

    No Known Activations