© 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. 63718
    Prev
    Next
    INDEX
    Explanations

    retired French or Ecuadorian

    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
    èªĺ
    -0.08
    祷
    -0.08
    swer
    -0.08
    ocene
    -0.08
    æ´Ľå¤«
    -0.07
    AILS
    -0.07
     ÑĢоÑĤ
    -0.07
     diger
    -0.07
    UNCT
    -0.07
    omics
    -0.07
    POSITIVE LOGITS
     negativity
    0.09
     negative
    0.08
     invariant
    0.08
     Negative
    0.07
    negative
    0.07
    ValueType
    0.07
    -negative
    0.07
    åĪº
    0.07
    è¯Ħ
    0.07
    ierarchy
    0.07
    Activations Density 0.001%

    No Known Activations