© 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. 62337
    Prev
    Next
    INDEX
    Explanations

    firewall restrict permissions

    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
    å¦ĸåŃ½
    -0.07
    atoon
    -0.07
    æijĬ
    -0.07
    æĭīæīĭ
    -0.07
    atkan
    -0.06
    jumbotron
    -0.06
    غÙħ
    -0.06
    å¹³åĿĩæ°´å¹³
    -0.06
    è¿Ń
    -0.06
    wers
    -0.06
    POSITIVE LOGITS
    éĻIJåĪ¶
    0.24
    éĻIJåĪ¶çļĦ
    0.21
     restriction
    0.21
     restricting
    0.21
    éĻIJåĪ¶äºĨ
    0.21
     restrict
    0.21
    çļĦéĻIJåĪ¶
    0.20
     restrictions
    0.20
     restricted
    0.19
    éĻIJåĪ¶æĢ§
    0.19
    Activations Density 0.485%

    No Known Activations