© 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. 21908
    Prev
    Next
    INDEX
    Explanations

    example and sample

    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
    и
    -0.07
    punk
    -0.07
    gings
    -0.06
    redient
    -0.06
    åįĵè¶ĬçļĦ
    -0.06
    çļĦåħ¸åŀĭ
    -0.06
    iated
    -0.06
    æľī好
    -0.06
    iating
    -0.06
    ÃŃo
    -0.05
    POSITIVE LOGITS
    Äįan
    0.05
    alb
    0.05
     Cruise
    0.05
    æ³ķå¸Ī
    0.05
    creds
    0.05
    åĪĽ
    0.05
    erman
    0.05
    åij¨åħ¨
    0.05
    æĹłéĤª
    0.05
     thuáºŃt
    0.05
    Activations Density 0.009%

    No Known Activations