© 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. 49989
    Prev
    Next
    INDEX
    Explanations

    variable assignment separator

    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
    usterity
    -0.12
    ivet
    -0.10
    -plus
    -0.10
    ardi
    -0.10
    ides
    -0.10
    ucci
    -0.10
    âĢ¦and
    -0.10
     indeb
    -0.10
    âĢ¦but
    -0.10
    -es
    -0.09
    POSITIVE LOGITS
     simult
    0.10
    chor
    0.10
     meanwhile
    0.09
     then
    0.09
     Soon
    0.09
     reform
    0.08
     simultaneously
    0.08
    torrent
    0.08
     lic
    0.08
    alla
    0.08
    Activations Density 0.004%

    No Known Activations