© 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. 39905
    Prev
    Next
    INDEX
    Explanations

    languages

    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
    ARK
    -0.09
    oundary
    -0.07
    äºĭä¸ļåįķä½įåħ¬å¼ĢæĭĽèģĺ
    -0.07
    ä¸įèĢĥèĻij
    -0.07
    ewise
    -0.07
    çĻ½çº¸
    -0.07
    scal
    -0.06
    èĢĥèĻijçļĦ
    -0.06
    åŁł
    -0.06
     Scal
    -0.06
    POSITIVE LOGITS
    çīĪ
    0.09
    -speaking
    0.08
    çīĪçļĦ
    0.08
    aml
    0.08
     flu
    0.08
    èķī
    0.07
    ocal
    0.07
     version
    0.07
    éªĨ
    0.06
    临å®ī
    0.06
    Activations Density 0.026%

    No Known Activations