© 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. 16971
    Prev
    Next
    INDEX
    Explanations

    list indexing and slicing

    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
    presenta
    -0.06
    iro
    -0.05
    ib
    -0.05
    cadena
    -0.05
    ногда
    -0.05
    er
    -0.05
     vio
    -0.05
    copy
    -0.05
    éĩĩ
    -0.05
    ibri
    -0.05
    POSITIVE LOGITS
    eties
    0.07
    ÑıÑĤи
    0.07
    ervo
    0.07
    oges
    0.06
    égal
    0.06
    óf
    0.06
    rup
    0.06
     кваÑĢÑĤ
    0.06
    oux
    0.06
    èvres
    0.06
    Activations Density 0.003%

    No Known Activations