© 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. 111530
    Prev
    Next
    INDEX
    Explanations

    not followed by a state

    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
    ece
    -0.09
     compar
    -0.09
     Werner
    -0.09
     purposely
    -0.08
    ikes
    -0.08
     konk
    -0.08
    ever
    -0.08
     circ
    -0.08
     Whip
    -0.08
     misunderstood
    -0.08
    POSITIVE LOGITS
     available
    0.11
     allowed
    0.11
    tingham
    0.11
     Mast
    0.11
     found
    0.10
     responding
    0.10
     Fir
    0.10
     AVAILABLE
    0.10
     monot
    0.09
    loat
    0.09
    Activations Density 0.243%

    No Known Activations