© 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. 21110
    Prev
    Next
    INDEX
    Explanations

    raise finance, donations, funds

    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
    oriously
    -0.08
    ÙĦØ©
    -0.07
    otr
    -0.06
    aters
    -0.06
    еÑĤа
    -0.06
    kring
    -0.06
    ยà¹Į
    -0.06
    ially
    -0.06
    HEMA
    -0.06
    çĶŁå¾Ĵ
    -0.06
    POSITIVE LOGITS
    ais
    0.07
    athan
    0.07
    Ñı
    0.06
    fulness
    0.06
    elves
    0.06
    ese
    0.06
    ä¼ı
    0.06
    upaya
    0.06
    iais
    0.05
    бÑĥдÑĮÑĤе
    0.05
    Activations Density 0.013%

    No Known Activations