© 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. 113087
    Prev
    Next
    INDEX
    Explanations

    another thing i noticed

    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
     Lowe
    -0.10
     maneuver
    -0.10
    rup
    -0.10
     Absolute
    -0.10
    eren
    -0.09
     absolute
    -0.09
    ìľĦ
    -0.09
     scour
    -0.09
     again
    -0.09
     meet
    -0.09
    POSITIVE LOGITS
     factor
    0.12
     contributing
    0.11
    oyer
    0.11
     equally
    0.10
     besides
    0.10
     aspect
    0.10
     noteworthy
    0.10
     complic
    0.10
    factor
    0.10
     important
    0.09
    Activations Density 0.019%

    No Known Activations