© 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. 17824
    Prev
    Next
    INDEX
    Explanations

    to followed by verbs

    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
    ×ŀ×Ļ×ĵ
    -0.06
    .cgi
    -0.05
    body
    -0.05
    åįĹè·¯
    -0.05
    uts
    -0.05
    razio
    -0.05
    修缮
    -0.05
    ibir
    -0.05
    повÑĸд
    -0.05
    etails
    -0.05
    POSITIVE LOGITS
    æīįèĥ½çľŁæŃ£
    0.07
    ä¸įå¾Ĺä¸į
    0.06
    幸
    0.06
    æīįå¾Ĺ以
    0.06
    æīį
    0.06
    anship
    0.06
    _limits
    0.06
    æĭ½
    0.05
    rof
    0.05
    éĿĻèĦī
    0.05
    Activations Density 0.047%

    No Known Activations