© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16760
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun or article after conjunction/preposition

    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
    Negative Logits
    allo
    -0.07
    æĪĺçķ¥åIJĪä½ľåįıè®®
    -0.06
    rek
    -0.06
    Ñħодим
    -0.06
     bail
    -0.06
    ajo
    -0.06
    кÑĢепиÑĤÑĮ
    -0.06
    éĩįçĤ¹é¢ĨåŁŁ
    -0.06
    elage
    -0.05
     kontrak
    -0.05
    POSITIVE LOGITS
     zami
    0.06
    æ¨Ĭ
    0.04
    壹
    0.04
    emu
    0.04
     mue
    0.04
    èĢ»
    0.04
    -inspired
    0.04
    rance
    0.04
    intr
    0.04
    n
    0.04
    Activations Density 0.008%

    No Known Activations