© 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. 18215
    Prev
    Next
    INDEX
    Explanations

    symbols and indicators

    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
    utter
    -0.05
    ວ
    -0.05
    odor
    -0.05
    gar
    -0.05
    !--
    -0.05
    åĻ
    -0.05
     Tear
    -0.05
    åĬ¨äºĨ
    -0.04
    éĢģ
    -0.04
    ower
    -0.04
    POSITIVE LOGITS
    计
    0.06
     báºŃc
    0.06
    prud
    0.05
    ney
    0.05
    æĭįæīĭ
    0.05
    boom
    0.05
    ä¸ī个éĺ¶æ®µ
    0.05
     Horton
    0.05
    hea
    0.05
     dumps
    0.05
    Activations Density 0.015%

    No Known Activations