© 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. 22129
    Prev
    Next
    INDEX
    Explanations

    again, followed by punctuation

    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
    bras
    -0.06
     Wib
    -0.06
    æĤ£
    -0.06
    ÃŃas
    -0.06
    fas
    -0.06
    éĢ£
    -0.06
    大åIJį
    -0.06
    fond
    -0.06
    è¿ŀ
    -0.06
    Ads
    -0.06
    POSITIVE LOGITS
    ä½ĵéªĮé¦Ĩ
    0.06
    annon
    0.05
    åħĪåĪ°åħĪå¾Ĺ
    0.05
    ä¸įçŁ¥éģĵ该
    0.05
    gression
    0.05
    åħĭ森
    0.05
    cision
    0.05
    dz
    0.05
    çĶŁçī©åѦ
    0.05
    ress
    0.05
    Activations Density 0.008%

    No Known Activations