© 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. 22179
    Prev
    Next
    INDEX
    Explanations

    title, headers, links

    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
    egy
    -0.06
     mer
    -0.06
    æ²Ļ
    -0.05
    .expect
    -0.05
     imm
    -0.05
    èµĦæĸĻ
    -0.05
    ossi
    -0.05
    áºŃt
    -0.05
    'aff
    -0.05
    synthesize
    -0.04
    POSITIVE LOGITS
    åIJ¯èĪª
    0.07
    èĢĮå·²
    0.06
    -yyyy
    0.06
    lettere
    0.06
    ä¸īæĽ´
    0.06
    inscrit
    0.06
    atorii
    0.06
    cats
    0.06
    ergie
    0.06
    ä¸ĩ人
    0.06
    Activations Density 0.010%

    No Known Activations