© 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. 22035
    Prev
    Next
    INDEX
    Explanations

    embracing technology, take risks

    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
     Noticed
    -0.06
     Guadal
    -0.06
    aire
    -0.06
    -Sah
    -0.05
    éĿłå±±
    -0.05
    ise
    -0.05
    igne
    -0.05
    ye
    -0.05
    çļĦåħ³éĶ®æĹ¶æľŁ
    -0.05
     ante
    -0.05
    POSITIVE LOGITS
    usche
    0.07
    линг
    0.06
    éĴīåŃIJ
    0.06
    Ñĭн
    0.06
    stdint
    0.06
    èį¼
    0.06
    ÃŃch
    0.05
     potentially
    0.05
    ÑĤинÑĭ
    0.05
    ugel
    0.05
    Activations Density 0.002%

    No Known Activations