© 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. 17871
    Prev
    Next
    INDEX
    Explanations

    particularly

    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
    ungan
    -0.08
    ghi
    -0.08
     поÑģл
    -0.08
    éĢ£éİĸ
    -0.07
    noon
    -0.07
    мка
    -0.07
    å·²ç»ıç»ĵæĿŁ
    -0.07
    yra
    -0.07
    OLA
    -0.07
     Geneva
    -0.07
    POSITIVE LOGITS
     liberties
    0.07
     maths
    0.07
    æĥ«
    0.07
    è§ħ
    0.06
    æŃ¹
    0.06
    éģįåıĬ
    0.06
    ساب
    0.06
    è®°å¾Ĺ
    0.06
     lod
    0.06
     Du
    0.06
    Activations Density 0.001%

    No Known Activations