© 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. 112223
    Prev
    Next
    INDEX
    Explanations

    id and group identifiers

    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
     relational
    -0.11
     isc
    -0.10
    --,
    -0.09
     alist
    -0.09
    —they
    -0.09
    —or
    -0.09
    ?url
    -0.09
     adr
    -0.08
     homosex
    -0.08
     bliss
    -0.08
    POSITIVE LOGITS
     ppl
    0.15
     replied
    0.15
     replies
    0.15
     reply
    0.14
     :(
    0.14
     [
    0.14
     pics
    0.14
     (@
    0.13
     Reply
    0.13
     emoji
    0.13
    Activations Density 0.009%

    No Known Activations