© 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. 21697
    Prev
    Next
    INDEX
    Explanations

    code syntax with parentheses

    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
    eldo
    -0.06
     obv
    -0.06
     assure
    -0.06
    جÙĩÙĪد
    -0.06
    æĪijåıijçİ°
    -0.06
    ked
    -0.05
    endam
    -0.05
    è°Ń
    -0.05
    hés
    -0.05
    æĪijå¾Ī
    -0.05
    POSITIVE LOGITS
    çģ«ä¸Ĭ
    0.05
    åĢĺ
    0.05
    atter
    0.05
    ÙĬرة
    0.05
    åħħåĪĨ
    0.05
    空åīį
    0.05
    åĢŁæ¬¾åIJĪåIJĮ
    0.05
    åĨ³å®ļçļĦ
    0.05
    istol
    0.05
    åħħåĪĨçļĦ
    0.05
    Activations Density 0.047%

    No Known Activations