© 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. 30304
    Prev
    Next
    INDEX
    Explanations

    sharp increase or intensity

    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
     Plum
    -0.11
     diffuse
    -0.10
     bulk
    -0.10
    ipse
    -0.10
    -over
    -0.10
     Tür
    -0.09
    ovah
    -0.09
     bulky
    -0.09
    ofs
    -0.09
     Bulk
    -0.09
    POSITIVE LOGITS
     edged
    0.17
     sharply
    0.17
     sharper
    0.16
    -ed
    0.15
    -cut
    0.15
     sharp
    0.15
    -eyed
    0.14
    -corner
    0.14
     wit
    0.14
    -point
    0.13
    Activations Density 0.045%

    No Known Activations