© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 45995
    Prev
    Next
    INDEX
    Explanations

    waiver override

    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
    Negative Logits
    edly
    -0.08
    tit
    -0.08
     deliberate
    -0.08
    ','%
    -0.08
    xious
    -0.08
     blurry
    -0.08
     Buen
    -0.08
    iring
    -0.08
    blur
    -0.08
    Blur
    -0.08
    POSITIVE LOGITS
     sheer
    0.11
    ambi
    0.10
    ummer
    0.10
    sst
    0.10
    uda
    0.09
    dur
    0.09
    oy
    0.09
    enor
    0.09
    nown
    0.09
    eken
    0.09
    Activations Density 0.284%

    No Known Activations