© 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. 18196
    Prev
    Next
    INDEX
    Explanations

    optimize performance

    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
    äºĭçļĦ
    -0.07
    jera
    -0.06
    ÙĪارÙĩ
    -0.06
    ement
    -0.06
    ÙĪات
    -0.05
    ؤÙĦاء
    -0.05
    äºĭä¸Ń
    -0.05
    rement
    -0.05
     itib
    -0.05
    _weak
    -0.05
    POSITIVE LOGITS
    度è¿ĩ
    0.06
    адÑĮ
    0.06
    olon
    0.06
    ouse
    0.06
    æ§ĺ
    0.06
    ambo
    0.06
    going
    0.06
    ungk
    0.06
    驾
    0.06
    é§ķ
    0.06
    Activations Density 0.006%

    No Known Activations