© 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. 19915
    Prev
    Next
    INDEX
    Explanations

    a lot of

    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
    obel
    -0.07
    беÑĢна
    -0.07
    ÙĪØ¡
    -0.06
    ering
    -0.06
    ×IJ×ķת
    -0.06
    éf
    -0.06
    timi
    -0.06
    اÙģÙĦØ©
    -0.06
    oes
    -0.06
    INGS
    -0.06
    POSITIVE LOGITS
    i
    0.06
    as
    0.06
     needs
    0.05
    an
    0.05
    de
    0.05
    kog
    0.05
    æľīå¿ħè¦ģ
    0.05
    èµĺ
    0.05
     tá»ij
    0.05
     absolut
    0.05
    Activations Density 0.018%

    No Known Activations