© 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. 18127
    Prev
    Next
    INDEX
    Explanations

    comparisons of size and quantity

    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
    cod
    -0.08
     deficit
    -0.07
    ç¾İæĸĩ
    -0.07
     feh
    -0.07
    çIJīçĴĥ
    -0.07
    ׳ק
    -0.07
    åĬŁçĶ¨
    -0.07
     deficiency
    -0.07
    Peer
    -0.07
    åŃ°
    -0.07
    POSITIVE LOGITS
    ki
    0.07
    åīª
    0.07
     prune
    0.07
    sparse
    0.07
     pruning
    0.07
     sparse
    0.07
    åıijçļĦ
    0.07
    ä¹±
    0.07
     amort
    0.07
     truly
    0.07
    Activations Density 0.007%

    No Known Activations