© 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. 21897
    Prev
    Next
    INDEX
    Explanations

    let's

    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
    acin
    -0.08
    hton
    -0.06
    è¨Ģä¹ĭ
    -0.05
    ument
    -0.05
    çĶŁçĶŁ
    -0.05
    ä¸İæľ¬
    -0.05
    æľ¬çīĪ
    -0.05
    opil
    -0.05
    unde
    -0.05
    ocop
    -0.05
    POSITIVE LOGITS
    گاÙĩ
    0.06
    繫
    0.06
    æī¿
    0.06
    пÑĤ
    0.05
    สà¸Ļ
    0.05
     hoor
    0.05
    åĴ§åĺ´
    0.05
    een
    0.05
    ç³»çļĦ
    0.05
    âĢ¦the
    0.05
    Activations Density 0.017%

    No Known Activations