© 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. 18942
    Prev
    Next
    INDEX
    Explanations

    metabolism, metabolic processes, diseases

    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
    ifies
    -0.08
    ifier
    -0.07
     Juta
    -0.07
    unities
    -0.07
    ified
    -0.07
    ify
    -0.07
    æľīåĬĽçļĦ
    -0.06
    à¸Ĭัย
    -0.06
    ification
    -0.06
    ered
    -0.06
    POSITIVE LOGITS
    Ù°
    0.06
    opil
    0.06
    kah
    0.06
    ارÙģ
    0.06
    ried
    0.05
    Č
    0.05
    atem
    0.05
    _stderr
    0.05
    oret
    0.05
    letcher
    0.05
    Activations Density 0.036%

    No Known Activations