© 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. 56821
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    lec
    -0.08
    yka
    -0.08
    leben
    -0.07
    åIJ»
    -0.07
    omin
    -0.07
    iato
    -0.07
    çĶŁæ´»
    -0.06
    çĶŁåij½
    -0.06
    Ïģκ
    -0.06
    ltre
    -0.06
    POSITIVE LOGITS
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    åĬłæĭ¿å¤§
    0.08
    åĨįåĬłä¸Ĭ
    0.07
     respective
    0.07
    åıĪæĪĸèĢħ
    0.07
    [](
    0.07
    æĭŃ缮
    0.06
    <|box_end|>
    0.06
    etc
    0.06
    komsten
    0.06
    Activations Density 0.076%

    No Known Activations