© 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. 91324
    Prev
    Next
    INDEX
    Explanations

    may or may 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
    reck
    -0.10
     seiz
    -0.10
    ermen
    -0.10
    fal
    -0.09
     dav
    -0.09
     uu
    -0.09
     reckon
    -0.09
     sca
    -0.09
     particular
    -0.09
    /re
    -0.09
    POSITIVE LOGITS
     Neh
    0.10
     Kirst
    0.10
     may
    0.09
     Ish
    0.09
     decentral
    0.08
     overlap
    0.08
     monoc
    0.08
    ville
    0.08
    aria
    0.08
     Acad
    0.08
    Activations Density 0.010%

    No Known Activations