© 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. 21235
    Prev
    Next
    INDEX
    Explanations

    code identifiers or file paths

    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
    ning
    -0.05
    rie
    -0.05
    稼
    -0.05
    Âł
    -0.05
     Lov
    -0.05
    inn
    -0.04
    ç¹ģ
    -0.04
    it
    -0.04
     ÑģоÑĩеÑĤ
    -0.04
    iov
    -0.04
    POSITIVE LOGITS
     Ùħجد
    0.07
    vky
    0.07
    agraph
    0.07
    æIJŃä¸Ĭ
    0.07
    guá»ĵn
    0.07
     tenden
    0.06
     adicionales
    0.06
    plo
    0.06
    thy
    0.06
     psy
    0.06
    Activations Density 0.024%

    No Known Activations