© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21515
    Prev
    Next
    INDEX
    Explanations

    forms of address and names

    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
    åĴĮçĶ°
    -0.06
    åIJİæľī
    -0.06
    åıĪæľī
    -0.06
    ä¼ĺåĬ¿
    -0.06
    ched
    -0.06
    üglich
    -0.05
     elder
    -0.05
    ajo
    -0.05
    topl
    -0.05
     PLATFORM
    -0.05
    POSITIVE LOGITS
    ux
    0.06
    ringe
    0.05
    los
    0.05
    ight
    0.05
    ogo
    0.05
    гÑĥ
    0.05
    igh
    0.05
    .present
    0.05
     unprotected
    0.05
    è¿Ļç§įä¸ľè¥¿
    0.05
    Activations Density 0.002%

    No Known Activations