© 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. 25731
    Prev
    Next
    INDEX
    Explanations

    letter b or code characters

    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
    ]={
    -0.07
    POCH
    -0.07
    è¿Ľ
    -0.07
    åĪĩå®ŀåģļåĪ°
    -0.06
    éĢ²
    -0.06
    ADI
    -0.06
    (pt
    -0.06
    ÏĦÏį
    -0.06
    èIJ½åĪ°å®ŀå¤Ħ
    -0.06
     lata
    -0.06
    POSITIVE LOGITS
    æīįèĥ½è®©
    0.07
    æľ«
    0.07
    èĢĮçĶŁ
    0.07
    äst
    0.07
    èĢĮç«ĭ
    0.07
    ç§
    0.07
    .measure
    0.07
    даÑĨии
    0.07
    æķı
    0.07
    æĥ³æĸ¹
    0.07
    Activations Density 0.025%

    No Known Activations