© 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. 20927
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    g
    -0.06
    å¯¹é¡¹çĽ®
    -0.05
    alog
    -0.05
    so
    -0.05
    lik
    -0.05
    log
    -0.05
    个ä¸ĵä¸ļ
    -0.05
    ouch
    -0.05
    isi
    -0.05
    å¤ļä¸ĩåħĥ
    -0.05
    POSITIVE LOGITS
    árn
    0.07
    utate
    0.06
    еÑī
    0.06
    esn
    0.06
    indu
    0.06
     forn
    0.06
     Kalim
    0.06
    аÑĤÑĥÑĢ
    0.05
     meanwhile
    0.05
    æıIJä¾Ľä¸Ģç§į
    0.05
    Activations Density 0.064%

    No Known Activations