© 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. 17607
    Prev
    Next
    INDEX
    Explanations

    mathematical and conditional statements

    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
    æĹłæĺİæĺ¾
    -0.05
     inf
    -0.05
    å½ĵåľ°
    -0.05
    andang
    -0.05
    rific
    -0.05
     оÑĤÑĢ
    -0.05
    æ°ij
    -0.05
    çĴ
    -0.05
    em
    -0.05
    åĪ
    -0.05
    POSITIVE LOGITS
    èĵĿèī²åŃĹä½ĵ
    0.07
    ä¼ĺèī¯
    0.06
    çĥ¨
    0.06
    建çŃijé£İæł¼
    0.06
    ombe
    0.06
    çĶµç«Ļ
    0.06
     Came
    0.06
    ingend
    0.05
     ÙĬÙĨب
    0.05
    chino
    0.05
    Activations Density 0.001%

    No Known Activations