© 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. 18098
    Prev
    Next
    INDEX
    Explanations

    how to

    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
    äºľ
    -0.05
    grado
    -0.05
    à¹ģà¸ĭ
    -0.05
    ack
    -0.05
    ately
    -0.05
    æł
    -0.05
     millis
    -0.05
    æĮĩ导ä¸ĭ
    -0.05
    autop
    -0.05
    ellt
    -0.05
    POSITIVE LOGITS
    thon
    0.06
    manship
    0.06
    æĹıèĩªæ²»
    0.06
    Äįov
    0.06
    kend
    0.06
    erty
    0.06
    è°ģä¹Ł
    0.06
    sene
    0.06
    sche
    0.06
     ÑģобÑĸ
    0.06
    Activations Density 0.027%

    No Known Activations