© 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. 31796
    Prev
    Next
    INDEX
    Explanations

    names and roles followed by 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
     flown
    -0.18
     beaten
    -0.16
     withdrawn
    -0.15
     drawn
    -0.14
     risen
    -0.14
     eaten
    -0.14
     thrown
    -0.12
     borne
    -0.12
     blown
    -0.12
     woven
    -0.12
    POSITIVE LOGITS
     has
    0.15
     simply
    0.14
     had
    0.13
     never
    0.12
    ’s
    0.12
    's
    0.12
     didn
    0.12
     cannot
    0.12
     knows
    0.11
     decided
    0.11
    Activations Density 1.066%

    No Known Activations