© 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. 92083
    Prev
    Next
    INDEX
    Explanations

    ending with 'sis' or 'ess'

    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
     Å
    -0.14
     Uhr
    -0.11
     Charl
    -0.10
    UpdateTime
    -0.10
     MacDonald
    -0.09
    leton
    -0.09
    apiKey
    -0.09
    enaire
    -0.09
     vielen
    -0.09
    ton
    -0.09
    POSITIVE LOGITS
     Gus
    0.22
     Ness
    0.22
    osis
    0.21
    esis
    0.20
    اس
    0.20
     NSS
    0.20
     Tess
    0.20
    ãĥ¼ãĤ¹
    0.20
     ISIS
    0.19
     Kis
    0.19
    Activations Density 1.911%

    No Known Activations