© 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. 32196
    Prev
    Next
    INDEX
    Explanations

    http followed by ://

    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
    ertime
    -0.08
    åħį费订éĺħ
    -0.08
    ercise
    -0.08
    rata
    -0.07
    个人页
    -0.07
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    -0.07
    è¯ļèģĺèĭ±æīį
    -0.07
    åħ¶å®ĥåªĴä½ĵ
    -0.07
    .gc
    -0.07
    ertz
    -0.07
    POSITIVE LOGITS
    ://
    0.08
    æĭĩ
    0.07
    able
    0.07
     accessed
    0.06
    lant
    0.06
    platz
    0.06
    ä¹ĭ家
    0.06
    elan
    0.06
    è¿Ħ
    0.06
     Accessed
    0.06
    Activations Density 0.098%

    No Known Activations