© 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. 17571
    Prev
    Next
    INDEX
    Explanations

    python libraries and data structures

    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
    leden
    -0.05
    对被
    -0.05
    Ľ
    -0.05
    orgia
    -0.05
     re
    -0.05
    ave
    -0.05
    ellas
    -0.05
    ello
    -0.05
    å¾Ħ
    -0.05
    ели
    -0.05
    POSITIVE LOGITS
    示èĮĥçĤ¹
    0.06
    du
    0.06
    åı¸ä»¤
    0.05
     Fighters
    0.05
     Ñģкладе
    0.05
    Aj
    0.05
    ovable
    0.05
    åĩºåħ¥
    0.05
    mage
    0.05
    延æŶ
    0.05
    Activations Density 0.004%

    No Known Activations