© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19630
    Prev
    Next
    INDEX
    Explanations

    Only followed by a specific condition or noun

    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
    ed
    -0.06
    ako
    -0.06
    -0.06
    们çļĦ
    -0.06
    ung
    -0.05
    ari
    -0.05
    foot
    -0.05
    ypo
    -0.05
    es
    -0.05
    лей
    -0.05
    POSITIVE LOGITS
    ities
    0.06
    itatea
    0.06
    ords
    0.06
     Amo
    0.06
    æĥħåĨµä¸ĭ
    0.06
    ertos
    0.06
    verg
    0.05
    stum
    0.05
    rophe
    0.05
    lah
    0.05
    Activations Density 0.016%

    No Known Activations