© 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. 21158
    Prev
    Next
    INDEX
    Explanations

    code examples and libraries

    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
    plin
    -0.06
    ogos
    -0.06
    anje
    -0.05
    èݹ
    -0.05
    ellig
    -0.05
    wick
    -0.05
     bite
    -0.05
     olmak
    -0.05
    lich
    -0.05
    åĽłæŃ¤åľ¨
    -0.05
    POSITIVE LOGITS
    borne
    0.07
    éĢĢ
    0.06
    天é¾Ļ
    0.05
    uso
    0.05
    è¡£è£Ļ
    0.05
    èĭĹ
    0.05
    大çİĭ
    0.05
    iau
    0.05
    ÙĤدÙĬÙħ
    0.05
    éĻħ
    0.05
    Activations Density 0.032%

    No Known Activations