© 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. 7630
    Prev
    Next
    INDEX
    Explanations

    subjectsenderrecipientrecipientsToSend

    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
     crumbs
    -0.10
     Suc
    -0.09
     biz
    -0.09
    ream
    -0.09
    arin
    -0.09
    incr
    -0.09
    /ns
    -0.09
     liking
    -0.09
     Hag
    -0.09
    ollo
    -0.08
    POSITIVE LOGITS
    ToSend
    0.10
    achen
    0.09
    mine
    0.09
     recipient
    0.09
    NAL
    0.09
     sender
    0.09
     mildly
    0.09
    ILI
    0.08
     mild
    0.08
     recipients
    0.08
    Activations Density 0.308%

    No Known Activations