© 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. 19383
    Prev
    Next
    INDEX
    Explanations

    leading to *is*

    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
    anj
    -0.06
    ibile
    -0.06
    ани
    -0.06
     admite
    -0.06
    apl
    -0.06
    даеÑĤÑģÑı
    -0.06
    rene
    -0.06
     Tew
    -0.06
    apor
    -0.06
    åľ¨å¿ĥéĩĮ
    -0.06
    POSITIVE LOGITS
     e
    0.06
    ä½įåľ¨
    0.06
    ļĮ
    0.05
    perc
    0.05
     democr
    0.05
    stack
    0.05
     libr
    0.05
    åIJĦç§ij
    0.05
    趣
    0.05
    aghan
    0.05
    Activations Density 0.002%

    No Known Activations