© 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. 19312
    Prev
    Next
    INDEX
    Explanations

    constituted by string properties

    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
    ich
    -0.06
    ych
    -0.05
    zell
    -0.05
    åħ¬åı¸åıĬ
    -0.05
    åĪ°å¤´
    -0.05
    nard
    -0.05
    nier
    -0.05
    åħ³äºİåģļ好
    -0.05
    avo
    -0.05
    æīĵ交éģĵ
    -0.05
    POSITIVE LOGITS
    oder
    0.06
    åħ¶ä¸Ń
    0.06
    ::-
    0.06
    æĮ¤
    0.05
    forme
    0.05
    !--
    0.05
    à§ĩশ
    0.05
    ê·¹
    0.05
    Af
    0.05
    à¸IJ
    0.05
    Activations Density 0.013%

    No Known Activations