© 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. 17416
    Prev
    Next
    INDEX
    Explanations

    Unsupported, follow, alcoholic, door, Editing, normal, faux

    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
    érés
    -0.06
    usste
    -0.06
    æs
    -0.06
    ÑĤни
    -0.05
    ÙĢ
    -0.05
     omas
    -0.05
    aleigh
    -0.05
    itys
    -0.05
     concre
    -0.05
    ndata
    -0.05
    POSITIVE LOGITS
    ÑģÑĤÑĮÑı
    0.06
    åĮ®
    0.06
     means
    0.06
    ost
    0.06
    enen
    0.05
    ede
    0.05
    çģĮ
    0.05
     imp
    0.05
     Means
    0.05
    ç»Ħéķ¿
    0.05
    Activations Density 0.006%

    No Known Activations