© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20759
    Prev
    Next
    INDEX
    Explanations

    out of control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertz
    -0.05
    anches
    -0.05
    idor
    -0.05
     delic
    -0.05
    utus
    -0.05
    cout
    -0.05
    sym
    -0.05
    urg
    -0.05
    èļĢ
    -0.05
    å§Ĩæĸ¯
    -0.05
    POSITIVE LOGITS
    igió
    0.06
    ä»ĸåıª
    0.06
     Turnbull
    0.06
    ETT
    0.06
    梨èĬ±
    0.06
    igli
    0.06
    mals
    0.06
    åĶ¯ä¸ĢçļĦ
    0.06
     tast
    0.06
    ç§ijæĬĢ大åѦ
    0.06
    Activations Density 0.012%

    No Known Activations