© 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. 20336
    Prev
    Next
    INDEX
    Explanations

    blind

    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
    naments
    -0.06
    æĪijå¿ħé¡»
    -0.05
    ampir
    -0.05
     khan
    -0.05
    xygen
    -0.05
    outine
    -0.05
    er
    -0.05
    eau
    -0.05
    æ¹ĸ滨
    -0.05
     Kro
    -0.05
    POSITIVE LOGITS
    ä¹İ
    0.07
    ness
    0.07
    blind
    0.06
    kert
    0.06
    illes
    0.06
    lessly
    0.06
    CTR
    0.06
    últ
    0.06
    gments
    0.06
    à¤Ĥत
    0.06
    Activations Density 0.008%

    No Known Activations