© 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. 7102
    Prev
    Next
    INDEX
    Explanations

    check for existence or status

    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
    awah
    -0.11
    cka
    -0.09
    vertisement
    -0.09
     wired
    -0.09
     cling
    -0.09
    -placeholder
    -0.08
    pedia
    -0.08
     strategically
    -0.08
     Permission
    -0.08
    &a
    -0.08
    POSITIVE LOGITS
     contributors
    0.11
     unpublished
    0.11
     subscribers
    0.10
     actual
    0.10
     unre
    0.10
     users
    0.10
     disg
    0.10
     names
    0.10
     incons
    0.10
    engl
    0.10
    Activations Density 0.016%

    No Known Activations