© 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. 17169
    Prev
    Next
    INDEX
    Explanations

    look after

    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
     to
    -0.09
     rend
    -0.09
    ogl
    -0.09
     looked
    -0.09
     pes
    -0.09
     glance
    -0.08
    ogn
    -0.08
    omi
    -0.08
    ook
    -0.08
     look
    -0.08
    POSITIVE LOGITS
    crate
    0.11
     freely
    0.10
     FORWARD
    0.10
    htar
    0.10
     feas
    0.10
     Dal
    0.09
    vik
    0.09
    .der
    0.09
     Faction
    0.09
    otos
    0.09
    Activations Density 0.031%

    No Known Activations