© 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. 17040
    Prev
    Next
    INDEX
    Explanations

    signing and signatures

    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
    brook
    -0.07
     MeÄiju
    -0.06
    çŃĽ
    -0.06
    itrine
    -0.06
     Trik
    -0.06
    æįħ
    -0.06
    creen
    -0.06
     Sawyer
    -0.06
     kunj
    -0.06
    篩
    -0.06
    POSITIVE LOGITS
    åĬĽçļĦ
    0.06
    ç»ĵåIJĪäºĨ
    0.05
     bond
    0.05
    ceau
    0.05
    çĽĸ
    0.05
    æ¶īåıĬåĪ°
    0.05
    ä¸įåı¯èĥ½
    0.05
     involving
    0.05
    °
    0.05
    dg
    0.05
    Activations Density 0.015%

    No Known Activations