© 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. 20882
    Prev
    Next
    INDEX
    Explanations

    sequences of Cs

    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
    TMP
    -0.07
    itus
    -0.07
    åĽ½éĻħè´¸æĺĵ
    -0.06
     rokov
    -0.06
    yne
    -0.06
    '&&
    -0.06
    "^
    -0.06
    cccc
    -0.06
    iton
    -0.06
    éĺħ
    -0.06
    POSITIVE LOGITS
     apt
    0.05
    æ³ĵ
    0.05
    人åĿĩ
    0.05
    é¹
    0.05
    ilha
    0.05
    4
    0.05
    足
    0.05
    ahas
    0.05
    ä¸Ģ带
    0.05
    è¿ĻåĽĽ
    0.04
    Activations Density 0.005%

    No Known Activations