© 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. 1251
    Prev
    Next
    INDEX
    Explanations

    combining values to achieve a specific outcome

    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
    é£İäºij
    -0.07
    çĺ¤
    -0.07
    åħį费注åĨĮ
    -0.07
    åĴĮçĪ±
    -0.07
     ròng
    -0.07
    åħ¨åľº
    -0.07
    é¦Ĩéķ¿
    -0.07
    زاÙħ
    -0.07
    agni
    -0.07
    cÃŃ
    -0.07
    POSITIVE LOGITS
    åĪĨå¸ĥ
    0.12
     distribution
    0.11
    Distribution
    0.11
     Distribution
    0.11
    åĪĨéħį
    0.11
     distributing
    0.11
     distributes
    0.10
     distribute
    0.10
    åĪĨéħįåĪ°
    0.10
    åĪĨéħįçļĦ
    0.10
    Activations Density 0.007%

    No Known Activations