© 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. 18372
    Prev
    Next
    INDEX
    Explanations

    .field names

    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
    —you
    -0.07
    æ¶Ľ
    -0.06
    /&
    -0.06
    !”.
    -0.06
    irin
    -0.06
    zem
    -0.06
    ãĢij,
    -0.06
    —if
    -0.06
     complet
    -0.06
    kori
    -0.06
    POSITIVE LOGITS
     subtil
    0.05
    对åħ¶è¿Ľè¡Į
    0.05
    iest
    0.05
    کارÛĮ
    0.05
     meaning
    0.05
    égard
    0.05
    对åħ¶
    0.05
    BLEM
    0.05
    embra
    0.05
     [
    0.05
    Activations Density 0.051%

    No Known Activations