© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19868
    Prev
    Next
    INDEX
    Explanations

    son of

    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
    lace
    -0.05
    iss
    -0.05
    throw
    -0.05
     terr
    -0.05
     establishment
    -0.05
     merged
    -0.05
    ENCE
    -0.05
     maybe
    -0.05
     whose
    -0.05
     uniform
    -0.05
    POSITIVE LOGITS
    impat
    0.07
    åĪĩç¢İ
    0.07
     Hort
    0.06
    fique
    0.06
    ãģ£ãģ¦ãģĹãģ¾ãģ£ãģŁ
    0.06
    umu
    0.06
    ëŀij
    0.06
    è¢ĸ
    0.06
    æĪŁ
    0.06
     dysk
    0.06
    Activations Density 0.054%

    No Known Activations