© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16209
    Prev
    Next
    INDEX
    Explanations

    including new

    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
    sic
    -0.11
     Jug
    -0.10
     pun
    -0.10
     Oc
    -0.09
     matches
    -0.09
     plung
    -0.09
     subur
    -0.09
     erg
    -0.09
     sek
    -0.09
     Sek
    -0.09
    POSITIVE LOGITS
     Why
    0.10
    Why
    0.09
    Tips
    0.09
    prech
    0.09
     Definition
    0.08
     Techniques
    0.08
     bev
    0.08
    zs
    0.08
     belie
    0.08
     Reasons
    0.08
    Activations Density 0.001%

    No Known Activations