© 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. 27416
    Prev
    Next
    INDEX
    Explanations

    also

    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
    hin
    -0.12
     additionally
    -0.12
    plus
    -0.11
    itech
    -0.11
    scr
    -0.11
     além
    -0.11
     besides
    -0.10
    cken
    -0.10
    ìĿ
    -0.10
     Sto
    -0.10
    POSITIVE LOGITS
     als
    0.14
     ALSO
    0.14
     also
    0.13
    ä¹Ł
    0.10
     Also
    0.08
    FINAL
    0.07
     ance
    0.07
    also
    0.07
    ãĤĤ
    0.07
    çº
    0.06
    Activations Density 0.360%

    No Known Activations