© 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. 21661
    Prev
    Next
    INDEX
    Explanations

    http header fields

    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
    éª
    -0.06
    é¨
    -0.05
    ibe
    -0.05
    ,input
    -0.05
    eam
    -0.05
     overlooking
    -0.05
    Compatible
    -0.05
    ere
    -0.05
    ocratic
    -0.05
    Ø·ÙĬÙĨ
    -0.05
    POSITIVE LOGITS
    inue
    0.07
    ÄĻd
    0.06
    afari
    0.06
    çĶ±çľģ
    0.06
    åħļæĢ»æĶ¯ä¹¦è®°
    0.06
    åĮ»åĺ±
    0.06
    涨åĬ¿
    0.05
    æĬ¥æĸĩ
    0.05
    +xml
    0.05
    æŃ¢è·Į
    0.05
    Activations Density 0.040%

    No Known Activations