© 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. 21230
    Prev
    Next
    INDEX
    Explanations

    men

    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
    ity
    -0.10
    nement
    -0.09
    erweise
    -0.08
    ...*
    -0.08
    ment
    -0.08
    æł·çļĦ
    -0.08
    able
    -0.07
    iance
    -0.07
    tır
    -0.07
    lah
    -0.07
    POSITIVE LOGITS
    jenigen
    0.08
    s
    0.07
    ãģĦãĤĭ
    0.05
    ÏĤ
    0.05
    keley
    0.05
    们
    0.05
    ãģĦãģŁ
    0.05
    kin
    0.05
    kov
    0.05
    Ñĥ
    0.05
    Activations Density 0.019%

    No Known Activations