© 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. 91338
    Prev
    Next
    INDEX
    Explanations

    he or she following 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
     hoped
    -0.13
     hope
    -0.12
     hopes
    -0.11
     deem
    -0.10
     invested
    -0.10
     regret
    -0.10
    hope
    -0.09
    /if
    -0.09
     remarks
    -0.09
     sincer
    -0.09
    POSITIVE LOGITS
     reminds
    0.20
     remind
    0.19
     belongs
    0.18
     reminded
    0.16
     resembles
    0.16
     belonged
    0.16
     belong
    0.15
     inspire
    0.15
     resemble
    0.14
     resembled
    0.14
    Activations Density 0.055%

    No Known Activations