© 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. 47628
    Prev
    Next
    INDEX
    Explanations

    delivery, Premier League, weaving, SCP ping, therapeutic, production, dwellings, Chagas'

    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
    bolo
    -0.07
    ÑģÑģоÑĢа
    -0.07
    被人们
    -0.07
    å°ıç¼ĸ为大家æķ´çIJĨçļĦ
    -0.07
    åĭ¤åĭ¤æģ³æģ³
    -0.07
    enska
    -0.07
    _scroll
    -0.07
    ä½ķå¤Ħ
    -0.07
    人æĺ¯
    -0.07
    achr
    -0.07
    POSITIVE LOGITS
     ((_
    0.08
    ]|[
    0.07
    åijĥ
    0.07
    <|im_end|>
    0.07
    ä¸ĭåIJĮ
    0.07
    âĢij
    0.07
    çon
    0.07
    /jav
    0.06
    ï¼ģï¼Ł
    0.06
    æĢ§æĪĸ
    0.06
    Activations Density 0.443%

    No Known Activations