© 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. 21017
    Prev
    Next
    INDEX
    Explanations

    titles, songs, poems, methods, characters, corporations, islands

    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
    ceria
    -0.06
    ï¸
    -0.06
    ä¼ļæ¯Ķè¾ĥ
    -0.05
    isser
    -0.05
    åħĭ
    -0.05
    иден
    -0.05
    èµ·äºĨ
    -0.05
    åĨ»ç»ĵ
    -0.05
    鹿
    -0.05
     protesto
    -0.05
    POSITIVE LOGITS
     occasionally
    0.06
    大åħ¬
    0.06
    —as
    0.06
    tons
    0.06
    dings
    0.05
    axy
    0.05
    çļĦåı«
    0.05
     desconhe
    0.05
    åĽĽæº¢
    0.05
    à¸ķั
    0.05
    Activations Density 0.323%

    No Known Activations