© 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. 33755
    Prev
    Next
    INDEX
    Explanations

    updating news or technical information

    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
    /per
    -0.10
     Feld
    -0.10
     MASTER
    -0.10
     reasonable
    -0.10
     grate
    -0.09
     recip
    -0.09
     singly
    -0.09
    hana
    -0.09
     wholes
    -0.09
    to
    -0.09
    POSITIVE LOGITS
    sei
    0.09
     offic
    0.09
     fix
    0.09
    /fixtures
    0.09
    chk
    0.08
     Bas
    0.08
     Constr
    0.08
     baseline
    0.08
     Candid
    0.08
     striped
    0.08
    Activations Density 0.003%

    No Known Activations