© 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. 20215
    Prev
    Next
    INDEX
    Explanations

    to be used

    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
    çĦ
    -0.07
    iliar
    -0.07
    akov
    -0.06
    åģļåĪ°
    -0.06
     абон
    -0.06
    ÃŃp
    -0.06
    ropped
    -0.06
    à¸ªà¸Ľ
    -0.06
    æİĤ
    -0.06
    spell
    -0.06
    POSITIVE LOGITS
    满æĦıçļĦ
    0.05
    à¦Łà¦¿
    0.05
    ¾
    0.05
     antaranya
    0.05
    åĬ¨æīĭ
    0.05
     direct
    0.05
     Diff
    0.05
     peri
    0.05
     finalmente
    0.04
     In
    0.04
    Activations Density 0.022%

    No Known Activations