© 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. 60544
    Prev
    Next
    INDEX
    Explanations

    ability

    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
    ionate
    -0.08
    _keywords
    -0.08
    aisser
    -0.07
    çݺ
    -0.07
    afen
    -0.07
    новÑĢемен
    -0.07
    èµ·æīĭ
    -0.07
    íķ©
    -0.07
    åĪĨå¤ĸ
    -0.07
    ignes
    -0.07
    POSITIVE LOGITS
    ability
    0.10
    èĥ½åĬĽ
    0.10
     capability
    0.10
     ability
    0.09
    èĥ½åĬĽå¼º
    0.08
    çļĦçī¹æĢ§
    0.08
    çļĦèĥ½åĬĽ
    0.08
    èĥ½åĬĽçļĦ
    0.08
    èĩªå¦Ĥ
    0.08
     abilities
    0.08
    Activations Density 0.389%

    No Known Activations