© 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. 48740
    Prev
    Next
    INDEX
    Explanations

    compete with or against

    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
    еж
    -0.09
     obedient
    -0.09
     drastically
    -0.09
    achable
    -0.08
     Hemp
    -0.08
     Faster
    -0.08
    udo
    -0.08
     wrath
    -0.08
    rc
    -0.08
    allet
    -0.08
    POSITIVE LOGITS
     toe
    0.19
     matched
    0.14
     handled
    0.11
     fend
    0.11
     against
    0.11
     match
    0.11
     evenly
    0.11
     handles
    0.10
     hold
    0.10
     handling
    0.10
    Activations Density 0.023%

    No Known Activations