© 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. 17995
    Prev
    Next
    INDEX
    Explanations

    class, struct, List, Link, Tree

    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
     threshold
    -0.05
     sk
    -0.05
    Threshold
    -0.05
    v
    -0.05
    ble
    -0.05
    天ä¸ĭ
    -0.05
     thresholds
    -0.04
    åģı移
    -0.04
     tit
    -0.04
    æ¯Ķåħ¶ä»ĸ
    -0.04
    POSITIVE LOGITS
    inch
    0.07
    peek
    0.06
    æľī空
    0.06
    çĶ¨çº¸
    0.06
    çĶ¨å¾Ĺ
    0.06
    ä¸Ģå¹ķ
    0.06
    Ñģив
    0.06
    ÙĤد
    0.06
    eree
    0.06
    åģļå®ŀ
    0.06
    Activations Density 0.021%

    No Known Activations