© 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. 30204
    Prev
    Next
    INDEX
    Explanations

    leiotropic, penetrant, interacting, plasticity

    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
    pires
    -0.08
     oble
    -0.07
    wick
    -0.07
    èĩªå¾Ĺ
    -0.07
    .ta
    -0.07
    VID
    -0.07
    ä¸ļçķĮ
    -0.07
    åħħçĽĪ
    -0.06
    staan
    -0.06
    ÈĻ
    -0.06
    POSITIVE LOGITS
     masking
    0.08
    LOY
    0.08
     affecting
    0.07
    修饰
    0.07
    boxing
    0.07
    aju
    0.07
     folding
    0.07
    vam
    0.07
     effects
    0.07
    è¿Ļæł·çļĦè¯Ŀ
    0.07
    Activations Density 0.001%

    No Known Activations