© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 22109
    Prev
    Next
    INDEX
    Explanations

    punctuation and thanks

    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
    mén
    -0.06
    лега
    -0.06
     namens
    -0.06
    浦路
    -0.06
    (ne
    -0.06
    isure
    -0.05
    º¼
    -0.05
     Neub
    -0.05
    æĪijæĺ¯ä¸ª
    -0.05
    ailer
    -0.05
    POSITIVE LOGITS
     clearly
    0.06
    wissen
    0.05
    opathic
    0.05
    åħ¬è®¤
    0.05
    kt
    0.05
    常è§ģéĹ®é¢ĺ
    0.05
    æ¸ħæ¥ļ
    0.05
     ages
    0.05
    åį°è¯ģ
    0.05
    land
    0.05
    Activations Density 0.005%

    No Known Activations