© 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. 17624
    Prev
    Next
    INDEX
    Explanations

    path manipulation in code

    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
     Cosby
    -0.07
    èģĺçĶ¨äººåijĺ
    -0.06
    åѦçłĶ究
    -0.06
    ndef
    -0.06
    åĤ¨è¿IJ
    -0.06
    ä¸ĢéŨ
    -0.06
    оÑĤÑĢе
    -0.06
    estin
    -0.06
    个ç¨İ
    -0.06
    .pa
    -0.06
    POSITIVE LOGITS
    符
    0.06
    aint
    0.05
    æľīæķĪçļĦ
    0.05
    ark
    0.05
    avn
    0.05
    æĬķ
    0.05
     supp
    0.05
    igu
    0.05
    æĤ¬
    0.05
    irc
    0.05
    Activations Density 0.037%

    No Known Activations