© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32181
    Prev
    Next
    INDEX
    Explanations

    -ism or -ery or -ing suffixes

    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
    ocene
    -0.13
    borne
    -0.11
    ional
    -0.11
     squeeze
    -0.11
    Warn
    -0.10
    ations
    -0.10
     Warn
    -0.10
    ings
    -0.10
    mos
    -0.10
     utmost
    -0.10
    POSITIVE LOGITS
    èĢħ
    0.15
    ners
    0.14
    ers
    0.13
    ERS
    0.13
    åĻ¨
    0.12
    ertype
    0.10
    gers
    0.09
    inters
    0.08
    ìŀIJ
    0.08
     fists
    0.08
    Activations Density 0.697%

    No Known Activations