© 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. 112696
    Prev
    Next
    INDEX
    Explanations

    claims and sources

    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
     clearly
    -0.11
     KNOW
    -0.09
    InSection
    -0.09
     obviously
    -0.09
     Remarks
    -0.09
     proves
    -0.09
     spender
    -0.09
     decisive
    -0.09
    397
    -0.08
     multiline
    -0.08
    POSITIVE LOGITS
     errone
    0.16
     alternatively
    0.16
     mistakenly
    0.15
     incorrectly
    0.15
     suggest
    0.15
    [at
    0.15
     claim
    0.15
     claimed
    0.14
     speculated
    0.13
     suggested
    0.13
    Activations Density 0.737%

    No Known Activations