© 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. 19071
    Prev
    Next
    INDEX
    Explanations

    .io extensions and related Java IO classes

    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
    engu
    -0.07
    боÑĢом
    -0.07
    ä¸Ģæī¶
    -0.06
    penas
    -0.06
    osta
    -0.06
    çĶ¨æĦı
    -0.06
    organisme
    -0.06
    åħ¨è·¯æ®µ
    -0.06
    bund
    -0.06
    angelo
    -0.06
    POSITIVE LOGITS
    à¹Ħหรà¹Ī
    0.07
    ÑĥÑĩ
    0.07
    er
    0.06
    лев
    0.06
    al
    0.06
    аем
    0.06
    ery
    0.06
    tienen
    0.06
    0.06
    æ·ij
    0.06
    Activations Density 0.018%

    No Known Activations