© 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. 112095
    Prev
    Next
    INDEX
    Explanations

    always/usually/often followed by a verb

    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
     slashing
    -0.08
     Cyr
    -0.08
    anches
    -0.07
     Dich
    -0.07
    orer
    -0.07
     Gree
    -0.07
     periodic
    -0.07
     revis
    -0.07
     Dec
    -0.07
     therap
    -0.07
    POSITIVE LOGITS
     seemed
    0.15
     seems
    0.13
     seem
    0.13
     dressed
    0.13
     seeming
    0.12
     insistence
    0.12
    atu
    0.12
     wears
    0.12
     exhaustion
    0.12
     insist
    0.12
    Activations Density 0.028%

    No Known Activations