© 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. 29794
    Prev
    Next
    INDEX
    Explanations

    .com / .net / .org / .gov / .gr

    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
    eldorf
    -0.08
    å¹³åľ°
    -0.07
    ommage
    -0.07
    afc
    -0.07
    stad
    -0.07
    á»ijc
    -0.07
    fram
    -0.07
    ayer
    -0.07
    åµ
    -0.07
    .Assembly
    -0.07
    POSITIVE LOGITS
    ubar
    0.07
    åĭ¤
    0.06
    ä¸ªå·¥ä½ľ
    0.06
    ues
    0.06
    ivin
    0.06
    .groups
    0.06
    creativecommons
    0.06
    }@
    0.06
    åijĺçļĦ
    0.06
    bn
    0.06
    Activations Density 0.521%

    No Known Activations