© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18440
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and closings

    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
     vét
    -0.07
    ).-
    -0.06
    ķ
    -0.06
    å¸ħæ°ĶçļĦ
    -0.06
    æī¬çļĦ
    -0.06
    زÙĬÙĨ
    -0.06
    åģļæ³ķ
    -0.06
    å°Ķ夫
    -0.05
     journ
    -0.05
    çŁ¥éģĵåIJĹ
    -0.05
    POSITIVE LOGITS
    nest
    0.06
    bis
    0.06
    meister
    0.05
    iny
    0.05
    驳
    0.05
    andro
    0.05
    æĪijåĴĮæĪijçļĦ
    0.05
    ç»ıåıĹ
    0.05
    inek
    0.05
    εκ
    0.05
    Activations Density 0.001%

    No Known Activations