© 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. 31682
    Prev
    Next
    INDEX
    Explanations

    there followed by is, are, 's, where, should

    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
    sWith
    -0.10
    sync
    -0.09
    roid
    -0.09
    tics
    -0.09
    earn
    -0.09
     latter
    -0.09
     notwithstanding
    -0.09
    sdk
    -0.09
    won
    -0.08
    ora
    -0.08
    POSITIVE LOGITS
     able
    0.17
     gonna
    0.17
     not
    0.13
     afraid
    0.13
     unable
    0.12
     meant
    0.12
    'e
    0.12
     aware
    0.11
     supposed
    0.11
     worth
    0.11
    Activations Density 0.041%

    No Known Activations