© 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. 19082
    Prev
    Next
    INDEX
    Explanations

    streets and avenues

    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
     real
    -0.06
    ê²½
    -0.06
    umm
    -0.05
     up
    -0.05
    çªij
    -0.05
     Samuel
    -0.05
     one
    -0.05
    çĦ¶çļĦ
    -0.05
     sam
    -0.05
     about
    -0.05
    POSITIVE LOGITS
    uida
    0.06
    istu
    0.06
    èĤ¡æĮĩ
    0.06
    æħİ
    0.06
    пли
    0.06
     bals
    0.06
    ved
    0.06
     premia
    0.06
     vél
    0.06
     trai
    0.06
    Activations Density 0.147%

    No Known Activations