© 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. 18202
    Prev
    Next
    INDEX
    Explanations

    subjects and their states

    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
    empf
    -0.07
    guns
    -0.06
    èĥĨ
    -0.06
    otland
    -0.06
    èĨ½
    -0.06
    éĥ½ä¸į好
    -0.06
    çľ·
    -0.06
     Ùħخاط
    -0.06
     epo
    -0.06
    åĩŃ
    -0.06
    POSITIVE LOGITS
    æ·±åİļçļĦ
    0.05
     materia
    0.05
    q
    0.05
     system
    0.05
    suming
    0.05
    è·¯ç«Ļ
    0.05
    indh
    0.05
    borough
    0.05
     ó
    0.05
     q
    0.05
    Activations Density 0.191%

    No Known Activations