© 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. 13501
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
    utow
    -0.08
    acci
    -0.08
    anks
    -0.07
    olia
    -0.07
     khá»ıi
    -0.07
    inales
    -0.07
    ebut
    -0.07
    æĹłä»¥
    -0.07
    ôte
    -0.07
    çĭ¬å®¶
    -0.07
    POSITIVE LOGITS
    å°Ķ夫
    0.07
    ergestellt
    0.07
    -ish
    0.07
    åİ»åIJ§
    0.06
    [âĢ¦]
    0.06
     opr
    0.06
    åijĹ
    0.06
    çķ¿
    0.06
    sic
    0.06
    istica
    0.06
    Activations Density 0.149%

    No Known Activations