© 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. 113581
    Prev
    Next
    INDEX
    Explanations

    in addition

    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
     Whale
    -0.09
    akk
    -0.09
    bastian
    -0.09
    anoia
    -0.09
    643
    -0.09
     ost
    -0.09
    vat
    -0.09
     precise
    -0.09
     perce
    -0.08
    -equiv
    -0.08
    POSITIVE LOGITS
     unrelated
    0.30
     related
    0.30
    related
    0.25
     Related
    0.23
    -related
    0.20
    Related
    0.18
    缸åħ³
    0.17
     RELATED
    0.17
     further
    0.15
     regards
    0.14
    Activations Density 0.186%

    No Known Activations