© 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. 19189
    Prev
    Next
    INDEX
    Explanations

    references `[@B``]`

    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
    eners
    -0.07
    åŁŁ
    -0.07
     dep
    -0.06
    pts
    -0.06
    hão
    -0.06
    dep
    -0.06
    expand
    -0.06
    ÙĦائ
    -0.06
    Endpoints
    -0.06
    luk
    -0.06
    POSITIVE LOGITS
    èªī
    0.08
    cium
    0.07
    vain
    0.07
    æĹ©å¹´
    0.07
     juste
    0.07
    IDA
    0.07
     (§
    0.07
    çªĿéĩĮ
    0.07
    -self
    0.07
    xmm
    0.07
    Activations Density 0.069%

    No Known Activations