© 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. 20893
    Prev
    Next
    INDEX
    Explanations

    biofilm

    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
    çĨ
    -0.05
    顺
    -0.05
     when
    -0.05
    ippi
    -0.05
    æĬĬä¸Ģ个
    -0.05
     contrast
    -0.05
    stance
    -0.05
    æĬĬ
    -0.05
     outgoing
    -0.05
     accidental
    -0.05
    POSITIVE LOGITS
    бÑĥÑĤ
    0.07
    大æ¦Ĥçİĩ
    0.07
    kea
    0.07
    $j
    0.07
    vor
    0.07
    arate
    0.07
     eventu
    0.07
     eventualmente
    0.06
    ç§ijçļĦ
    0.06
    мееÑĤÑģÑı
    0.06
    Activations Density 0.016%

    No Known Activations