© 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. 21975
    Prev
    Next
    INDEX
    Explanations

    old me, DC, controller, insect, in-proc

    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
    si
    -0.05
    lean
    -0.05
     si
    -0.05
    ~
    -0.05
     bore
    -0.05
     alike
    -0.05
    en
    -0.05
     kh
    -0.05
    è¯Ŀ
    -0.05
     je
    -0.04
    POSITIVE LOGITS
    ambi
    0.08
    ÑģÑĤÑĢи
    0.07
    olle
    0.06
    ÙĬص
    0.06
    æݪ并举
    0.06
    æľĪ份å¼Ģå§ĭ
    0.06
    çİ°åľ¨å¼Ģå§ĭ
    0.06
    Ñģей
    0.06
    .exchange
    0.06
    schied
    0.06
    Activations Density 0.199%

    No Known Activations