© 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. 47642
    Prev
    Next
    INDEX
    Explanations

    but not

    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
     schl
    -0.10
     cling
    -0.10
     inflated
    -0.10
     escorted
    -0.10
     acc
    -0.09
    hd
    -0.09
     Mall
    -0.09
     Rum
    -0.09
     Bun
    -0.09
    -no
    -0.09
    POSITIVE LOGITS
     bre
    0.17
     briefly
    0.17
    brief
    0.15
     suffice
    0.15
     brief
    0.14
    Brief
    0.14
     complex
    0.14
     exhaustive
    0.14
     space
    0.14
    complex
    0.14
    Activations Density 0.394%

    No Known Activations