© 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. 56627
    Prev
    Next
    INDEX
    Explanations

    degrees of freedom

    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
    eley
    -0.08
    égor
    -0.08
    ÄĥÈĻ
    -0.07
    æ·ij
    -0.07
    jong
    -0.07
    _kernel
    -0.07
     colega
    -0.07
    <|box_end|>
    -0.07
    è¾¾æĭī
    -0.07
    éĻ¢æīĢ
    -0.07
    POSITIVE LOGITS
    èĩªçĶ±åº¦
    0.09
     redundancy
    0.09
     redund
    0.08
    çĭ¬ç«ĭçļĦ
    0.08
     freedom
    0.08
     freely
    0.08
     independent
    0.08
     redundant
    0.08
    çļĦèĩªçĶ±
    0.07
     free
    0.07
    Activations Density 0.015%

    No Known Activations