© 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. 22245
    Prev
    Next
    INDEX
    Explanations

    from [noun/pronoun]

    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
    ordon
    -0.06
     prém
    -0.06
     daarom
    -0.06
    prud
    -0.05
    aura
    -0.05
    çħ§æł·
    -0.05
    chn
    -0.05
    ind
    -0.05
    æīĵæĿ¥
    -0.05
     plazas
    -0.05
    POSITIVE LOGITS
    lei
    0.06
    ited
    0.06
    under
    0.05
    èĤļåŃIJéĩĮ
    0.05
    forg
    0.05
     witnessing
    0.05
    عب
    0.05
    unci
    0.05
     inher
    0.05
    bei
    0.05
    Activations Density 0.003%

    No Known Activations