© 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. 21691
    Prev
    Next
    INDEX
    Explanations

    work with

    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
     SarÃł
    -0.08
    cidental
    -0.08
     ấn
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    ffi
    -0.07
    hers
    -0.07
    éĬ³
    -0.07
    deaux
    -0.07
     penget
    -0.07
     suaminya
    -0.07
    POSITIVE LOGITS
     "
    0.06
    è·Łè¸ª
    0.06
     p
    0.05
    av
    0.05
    ibir
    0.05
    åĪ¶
    0.05
    åįĬ
    0.05
    "
    0.05
    ç½®
    0.05
    ader
    0.04
    Activations Density 0.004%

    No Known Activations