© 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. 17619
    Prev
    Next
    INDEX
    Explanations

    punctuation and delimiters

    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
    RICS
    -0.06
    elado
    -0.06
    è±ģåħį
    -0.06
    chetto
    -0.06
    oppi
    -0.06
    olta
    -0.06
    æµĭ
    -0.06
    à¹Īม
    -0.06
    ç±ģ
    -0.06
    åħŃçĽĺ
    -0.06
    POSITIVE LOGITS
    ×Ļר×Ķ
    0.06
    ness
    0.06
    ward
    0.06
    formation
    0.06
    age
    0.05
    为ä¸Ĭ
    0.05
    heit
    0.05
    ron
    0.05
    us
    0.05
    gl
    0.05
    Activations Density 0.009%

    No Known Activations