© 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. 21436
    Prev
    Next
    INDEX
    Explanations

    =

    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
    beri
    -0.06
    anan
    -0.06
    بع
    -0.06
    anit
    -0.06
    untu
    -0.06
    indr
    -0.05
    sstr
    -0.05
    ؤ
    -0.05
    _track
    -0.05
    ianne
    -0.05
    POSITIVE LOGITS
    èĢĮå¤į
    0.05
     milho
    0.05
    еÑĢж
    0.05
    iously
    0.05
    lical
    0.05
    好å¤ļ
    0.05
    plast
    0.05
    ела
    0.05
    emerg
    0.05
    说
    0.05
    Activations Density 0.128%

    No Known Activations