© 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. 111737
    Prev
    Next
    INDEX
    Explanations

    lists of names and references

    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
    ‘s
    -0.08
    Evaluator
    -0.08
     likes
    -0.08
    /dist
    -0.08
    Envelope
    -0.08
    Latin
    -0.08
    vat
    -0.08
    wf
    -0.08
    ance
    -0.08
     Latin
    -0.08
    POSITIVE LOGITS
     kali
    0.10
     deltas
    0.09
     Instances
    0.09
    ?page
    0.09
     Kron
    0.09
     Instance
    0.09
     Ipsum
    0.09
     Featured
    0.08
     Vu
    0.08
     nearer
    0.08
    Activations Density 0.045%

    No Known Activations