© 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. 34023
    Prev
    Next
    INDEX
    Explanations

    extracting from

    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
     derived
    -0.12
    Derived
    -0.12
     borrowed
    -0.12
     deriving
    -0.12
     derive
    -0.11
     downloaded
    -0.11
     retrieved
    -0.10
     Derived
    -0.10
     lorem
    -0.10
    derived
    -0.10
    POSITIVE LOGITS
     from
    0.17
    from
    0.14
    /from
    0.13
    _from
    0.10
    	from
    0.10
     FROM
    0.09
     leaving
    0.09
    Formatted
    0.08
     fron
    0.08
     formatted
    0.08
    Activations Density 1.157%

    No Known Activations