© 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. 18179
    Prev
    Next
    INDEX
    Explanations

    relationship and Lists

    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
    延
    -0.05
    u
    -0.05
    ych
    -0.05
    å°¾
    -0.05
     postpone
    -0.05
     continu
    -0.05
     Fay
    -0.05
    zil
    -0.05
    ÙĪ
    -0.05
    ×ķ
    -0.05
    POSITIVE LOGITS
    Ø·
    0.06
    sav
    0.06
    ä¸ĭ称
    0.06
    agné
    0.06
    åľ°æŃ¥
    0.06
    sett
    0.06
    cepat
    0.06
     Improved
    0.06
    èĢĮæĿ¥
    0.06
    ìľ¡
    0.06
    Activations Density 0.007%

    No Known Activations