© 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. 15212
    Prev
    Next
    INDEX
    Explanations

    struggling 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
     snug
    -0.10
     invention
    -0.09
     perfectly
    -0.08
    rama
    -0.08
    agan
    -0.08
     trim
    -0.08
    eeper
    -0.08
     vriend
    -0.08
     seamlessly
    -0.08
    modifier
    -0.08
    POSITIVE LOGITS
     craw
    0.16
     attempt
    0.15
     attempts
    0.14
     crawl
    0.14
    /gr
    0.14
     crawled
    0.14
     attempting
    0.14
    åĭ
    0.14
    /cl
    0.13
     begr
    0.13
    Activations Density 0.039%

    No Known Activations