© 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. 111585
    Prev
    Next
    INDEX
    Explanations

    remove or removal of entries

    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
    lix
    -0.11
    ific
    -0.11
     Guth
    -0.11
    atorial
    -0.10
    waves
    -0.10
    ÃŃf
    -0.10
    wor
    -0.10
    rying
    -0.10
    `t
    -0.10
    wort
    -0.10
    POSITIVE LOGITS
    EmptyEntries
    0.11
    /disable
    0.10
    /add
    0.10
    /update
    0.09
    able
    0.09
    _from
    0.08
    /comment
    0.08
     from
    0.08
    -from
    0.08
     stains
    0.08
    Activations Density 0.043%

    No Known Activations