© 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. 38809
    Prev
    Next
    INDEX
    Explanations

    language specific terms

    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
    åħ¶äºº
    -0.08
    ä¸įè¿ĩä»ĸ
    -0.08
    ola
    -0.08
     оÑĤÑĤ
    -0.07
    以ä¸ĭåĨħ容
    -0.07
    ãĤĵãģ§ãģĹãĤĩãģĨ
    -0.07
    apai
    -0.07
    åħ¶æŀĹ
    -0.07
    allest
    -0.07
    Ef
    -0.07
    POSITIVE LOGITS
    urat
    0.07
     {*
    0.07
    å°ıç»Ħ
    0.06
     |âĢ¢
    0.06
    iet
    0.06
    _bind
    0.06
    ç»ĦåĽ¾
    0.06
    unbind
    0.06
    åĬ¨æīĭ
    0.06
    agin
    0.06
    Activations Density 0.009%

    No Known Activations