© 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. 17180
    Prev
    Next
    INDEX
    Explanations

    child

    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
    fli
    -0.06
    ä¸¥æł¼è¦ģæ±Ĥ
    -0.06
    uds
    -0.06
    .receive
    -0.05
    empf
    -0.05
    èĥĮéĿł
    -0.05
     Nodes
    -0.05
    éĿłå·¦
    -0.05
    ä¿ĿçķĻ
    -0.05
    èĬĤçĤ¹çļĦ
    -0.05
    POSITIVE LOGITS
     eriÅŁ
    0.06
    ibia
    0.06
    çĶµç½ij
    0.05
    -access
    0.05
    itat
    0.05
    ertia
    0.05
    èī²çļĦ
    0.05
     insulin
    0.05
    ft
    0.05
     irresist
    0.05
    Activations Density 0.017%

    No Known Activations