© 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. 17938
    Prev
    Next
    INDEX
    Explanations

    derivative wrt

    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
    erso
    -0.07
    inz
    -0.07
    venge
    -0.06
    dua
    -0.06
    é¨ĵ
    -0.06
     Relatives
    -0.06
     medic
    -0.06
    بع
    -0.06
     év
    -0.06
    檻
    -0.06
    POSITIVE LOGITS
    -types
    0.05
    ovel
    0.05
    æĺİçıł
    0.05
    ��
    0.05
    is
    0.05
    å°ij
    0.05
    Assigned
    0.04
    æ»ļ
    0.04
    uto
    0.04
    poly
    0.04
    Activations Density 0.053%

    No Known Activations