© 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. 17557
    Prev
    Next
    INDEX
    Explanations

    starting sentence with punctuation

    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
    æ²»çĸĹæĸ¹æ¡Ī
    -0.06
    Backing
    -0.05
    Nom
    -0.05
    å·¥ä½ľéľĢè¦ģ
    -0.05
    fuse
    -0.05
    ’S
    -0.05
    hoff
    -0.05
    ãģ£ãģĿ
    -0.05
    æķ´ä¸ªä¸ĸçķĮ
    -0.05
     testament
    -0.05
    POSITIVE LOGITS
     cad
    0.06
    oy
    0.05
    ilton
    0.05
    endis
    0.05
    å¾ģæĸĩ
    0.05
    appr
    0.05
    -relative
    0.05
     dimensions
    0.05
    onta
    0.05
     squarely
    0.05
    Activations Density 0.020%

    No Known Activations