© 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. 21220
    Prev
    Next
    INDEX
    Explanations

    punctuation and connecting words

    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
    uhan
    -0.06
    BER
    -0.06
    aser
    -0.05
    boll
    -0.05
    aż
    -0.05
     varm
    -0.05
    èĢĮåħ¥
    -0.05
    esta
    -0.05
     interr
    -0.05
    伯
    -0.05
    POSITIVE LOGITS
     décou
    0.06
     pé
    0.05
    sab
    0.05
    渴
    0.05
    akin
    0.05
    ieno
    0.05
    kelas
    0.05
    Projectile
    0.05
    max
    0.05
    æľīæķĪæľŁèĩª
    0.05
    Activations Density 0.057%

    No Known Activations