© 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. 88902
    Prev
    Next
    INDEX
    Explanations

    author bio date

    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
     bew
    -0.12
     Bew
    -0.11
     Huff
    -0.10
    jid
    -0.10
     ?:
    -0.10
     bef
    -0.10
    tot
    -0.09
     Isl
    -0.09
    :<?
    -0.09
     Tot
    -0.09
    POSITIVE LOGITS
    EDGE
    0.10
     prem
    0.08
     crud
    0.08
     Rit
    0.08
    ilage
    0.08
     Crud
    0.08
     preempt
    0.08
     cytok
    0.07
     interrog
    0.07
    cri
    0.07
    Activations Density 0.488%

    No Known Activations