© 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. 15573
    Prev
    Next
    INDEX
    Explanations

    selection, state, broker, Ra, service

    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
    ipa
    -0.07
    åĪļéľĢ
    -0.06
    Variant
    -0.06
    YLE
    -0.06
    _STATIC
    -0.06
     foro
    -0.06
    å°±å¦Ĥ
    -0.06
     ebooks
    -0.06
    éĩ
    -0.06
    .ReadAll
    -0.06
    POSITIVE LOGITS
    ìľ
    0.07
     Mystery
    0.07
    arrow
    0.06
    anzo
    0.06
     McConnell
    0.06
    äng
    0.06
    aven
    0.06
    éĤ¯
    0.06
    üst
    0.06
    éĥ´
    0.06
    Activations Density 0.004%

    No Known Activations