© 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. 17378
    Prev
    Next
    INDEX
    Explanations

    technical and related contexts

    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
    -0.05
     deck
    -0.05
    çļĦè¿Ļç§į
    -0.05
     ÑĨел
    -0.05
    og
    -0.05
    è¿Ľè¡ĮåĴ¨è¯¢
    -0.04
    ps
    -0.04
    以ä¸Ĭ
    -0.04
    mitted
    -0.04
    èĩ´çļĦ
    -0.04
    POSITIVE LOGITS
    weiler
    0.07
    puty
    0.07
    ety
    0.07
    äºĴèģĶäºĴéĢļ
    0.07
    olid
    0.06
    immä
    0.06
    еÑģп
    0.06
     mẽ
    0.06
    ľad
    0.06
    rung
    0.06
    Activations Density 0.004%

    No Known Activations