© 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. 21356
    Prev
    Next
    INDEX
    Explanations

    removing data structures methods

    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
    ç»Ī
    -0.05
    iness
    -0.05
    åĸĤ
    -0.05
    çļĦåīį
    -0.05
     ahead
    -0.05
     Conc
    -0.05
     жал
    -0.05
    æĬķ
    -0.05
    ütün
    -0.05
    åįķ缸
    -0.05
    POSITIVE LOGITS
    rede
    0.07
    ieme
    0.06
    éĽģ
    0.06
    emel
    0.06
    人åĸľæ¬¢
    0.06
    avo
    0.06
    urado
    0.06
    eração
    0.06
    εÏħ
    0.06
    vla
    0.06
    Activations Density 0.002%

    No Known Activations