© 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. 20121
    Prev
    Next
    INDEX
    Explanations

    one of each

    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
    ids
    -0.05
     E
    -0.05
     A
    -0.05
     Ñĩе
    -0.05
    ac
    -0.05
    akon
    -0.05
     B
    -0.05
     their
    -0.05
     C
    -0.05
    al
    -0.05
    POSITIVE LOGITS
    umpf
    0.07
     consu
    0.07
    gge
    0.06
    skou
    0.06
    åĪĽæĸ°åĴĮ
    0.06
    RAP
    0.06
    زاÙħ
    0.06
    iveau
    0.06
    еÑħа
    0.06
    .pet
    0.06
    Activations Density 0.052%

    No Known Activations