© 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. 17810
    Prev
    Next
    INDEX
    Explanations

    reporting research studies

    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
    Annotation
    -0.05
    WA
    -0.05
     ÐĶоб
    -0.05
    篤
    -0.05
    çļĦåij¢
    -0.05
    assin
    -0.05
    æĭ¿åľ°
    -0.05
    å½ĵãģŁãĤĬåīį
    -0.05
    ainter
    -0.05
    大çĻ½
    -0.05
    POSITIVE LOGITS
     kep
    0.06
    ï½¢
    0.05
    æĸ¹ä¾¿
    0.05
     Estimates
    0.05
     loop
    0.05
     Loop
    0.05
     اثر
    0.05
    bet
    0.05
    .Factory
    0.05
     fantasies
    0.05
    Activations Density 2.305%

    No Known Activations