© 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. 6980
    Prev
    Next
    INDEX
    Explanations

    tagged with

    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
     foresee
    -0.12
     Jag
    -0.11
     Cob
    -0.10
     proposals
    -0.10
     governments
    -0.09
     Granite
    -0.09
     foreseeable
    -0.09
     travers
    -0.09
    orpor
    -0.09
    ignet
    -0.09
    POSITIVE LOGITS
     nail
    0.09
     consum
    0.08
     PURE
    0.08
    nes
    0.08
    fest
    0.07
    aram
    0.07
    Cri
    0.07
     ridden
    0.07
     rar
    0.07
    858
    0.07
    Activations Density 0.041%

    No Known Activations