© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20494
    Prev
    Next
    INDEX
    Explanations

    not only

    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
    science
    -0.07
    quartered
    -0.07
    untr
    -0.07
    éĤĤ
    -0.06
    å¼ĢåĬŀ
    -0.06
     bois
    -0.06
     science
    -0.06
    Formats
    -0.06
    æ·¹
    -0.06
    écoute
    -0.06
    POSITIVE LOGITS
    ial
    0.05
    ä¸Ĭæŀ¶
    0.05
    intosh
    0.05
    ress
    0.04
    -
    0.04
    pled
    0.04
    erv
    0.04
     recal
    0.04
     domin
    0.04
    åIJİæŀľ
    0.04
    Activations Density 0.036%

    No Known Activations