© 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. 22034
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    regel
    -0.06
     peny
    -0.06
    好æĸĩ
    -0.06
    lemen
    -0.06
    çīĽè§Ĵ
    -0.06
    åħ¨åĬĽåģļ好
    -0.06
    å°Ĩè¾¾
    -0.06
    ãģłãģijãĤĴ
    -0.06
    rophy
    -0.06
    quanto
    -0.06
    POSITIVE LOGITS
    åĮħæĭ¬
    0.06
    odash
    0.06
    bose
    0.05
     including
    0.05
    ’
    0.05
    icht
    0.05
    èĤīçľ¼
    0.05
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.05
    å¦Ĥåıijçİ°
    0.05
    NSE
    0.05
    Activations Density 0.002%

    No Known Activations