© 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. 17464
    Prev
    Next
    INDEX
    Explanations

    directed graph

    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
     om
    -0.06
    åħ¨éĿ¢å¼Ģå±ķ
    -0.05
    unknown
    -0.05
     res
    -0.05
     diam
    -0.05
     Alternate
    -0.05
    alm
    -0.05
     pure
    -0.05
     Inter
    -0.05
    b
    -0.05
    POSITIVE LOGITS
    ä¸į对称
    0.07
    å®ļåIJij
    0.07
    tribute
    0.06
    epas
    0.06
    uela
    0.06
    tps
    0.06
     asym
    0.06
    mdir
    0.06
    VEST
    0.06
    ä¸įè¿ĺ
    0.06
    Activations Density 0.035%

    No Known Activations