© 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. 18235
    Prev
    Next
    INDEX
    Explanations

    always

    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
    anything
    -0.06
    imensional
    -0.06
    construct
    -0.06
     PN
    -0.05
    ector
    -0.05
    ĥ
    -0.05
    à¹Ģลยà¸Ĺีà¹Ģà¸Ķียว
    -0.05
    ater
    -0.05
    .fn
    -0.05
    ems
    -0.05
    POSITIVE LOGITS
    ries
    0.06
    оÑģÑĤав
    0.06
    åĽłä¸ºè¿ĻäºĽ
    0.06
    cky
    0.05
    æ°¸è¿ľ
    0.05
    umba
    0.05
    æĢ»æĺ¯
    0.05
     اÙĦتÙĪرÙĬد
    0.05
    驻马
    0.05
     вÑģегда
    0.05
    Activations Density 0.037%

    No Known Activations