© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 91248
    Prev
    Next
    INDEX
    Explanations

    Polish and Slavic words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    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
     wsz
    -0.16
     możli
    -0.13
     bÄĻdÄħ
    -0.13
     potrze
    -0.12
     majÄħ
    -0.12
     sobie
    -0.12
     też
    -0.12
     wÅĤa
    -0.11
     równ
    -0.11
     nawet
    -0.10
    POSITIVE LOGITS
     âĢŀ
    0.19
    âĢŀ
    0.18
     Polish
    0.16
     ,,
    0.16
     Åļ
    0.15
     additionally
    0.14
     Poland
    0.14
     dziew
    0.14
     Czech
    0.13
     Slovak
    0.13
    Activations Density 0.824%

    No Known Activations