© 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. 14587
    Prev
    Next
    INDEX
    Explanations

    grammatical categories | verbs

    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
    atha
    -0.10
    athe
    -0.10
     exceptionally
    -0.09
    thon
    -0.09
    epad
    -0.09
     doubtful
    -0.09
     staggering
    -0.08
     Seah
    -0.08
    ucker
    -0.08
    atte
    -0.08
    POSITIVE LOGITS
    ality
    0.12
    otten
    0.11
    als
    0.11
    osity
    0.11
     phrase
    0.10
    /action
    0.10
    /ad
    0.10
    illus
    0.10
     conjug
    0.10
    æ±
    0.10
    Activations Density 0.032%

    No Known Activations