© 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. 39344
    Prev
    Next
    INDEX
    Explanations

    bent, bending, or ends

    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
    级çļĦ
    -0.08
    odore
    -0.07
     dwind
    -0.07
    ä¸į详
    -0.07
     liá»ĩu
    -0.07
    ilÃł
    -0.07
     nghiá»ĩm
    -0.07
    istic
    -0.06
     Farr
    -0.06
     plenamente
    -0.06
    POSITIVE LOGITS
    /stretch
    0.10
    ioc
    0.10
    Ĺ
    0.10
    弧度
    0.08
     bend
    0.08
    å¼¯æĽ²
    0.08
    æĽ²
    0.08
    roc
    0.08
    edList
    0.08
     bends
    0.08
    Activations Density 0.028%

    No Known Activations