© 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. 32552
    Prev
    Next
    INDEX
    Explanations

    periods following text

    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
     Millennium
    -0.08
    cho
    -0.07
    http
    -0.07
    "
    -0.07
    äl
    -0.06
    çĥ¹è°ĥ
    -0.06
     Bottle
    -0.06
    æīij
    -0.06
     repet
    -0.06
    adies
    -0.06
    POSITIVE LOGITS
    åħļçļĦäºĮåįģ大
    0.08
    æł¸å¿ĥç´łåħ»
    0.08
    å®ĺ宣
    0.08
    íĮĶ
    0.08
     constexpr
    0.08
     TikTok
    0.08
    大湾åĮº
    0.08
    PROTO
    0.08
    ä¸Ńåįİä¼ĺç§Ģä¼łç»ŁæĸĩåĮĸ
    0.08
    łĢ
    0.08
    Activations Density 0.001%

    No Known Activations