© 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. 21479
    Prev
    Next
    INDEX
    Explanations

    selected | default

    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
    æīį被
    -0.06
    agence
    -0.05
    elten
    -0.05
    bare
    -0.05
    IANA
    -0.05
    vale
    -0.05
     lược
    -0.05
    strt
    -0.05
    pen
    -0.05
    Measured
    -0.05
    POSITIVE LOGITS
    ress
    0.06
    èı±
    0.06
    è¦ģæ±ĤåĴĮ
    0.05
    ause
    0.05
     multiple
    0.05
    水润
    0.05
    æķ°åŃĹ
    0.05
     repet
    0.05
    使ä¹ĭ
    0.05
    æīĭæı¡
    0.05
    Activations Density 0.020%

    No Known Activations