© 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. 13851
    Prev
    Next
    INDEX
    Explanations

    too much or very

    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
     nicely
    -0.14
     fluid
    -0.13
     Deg
    -0.13
     corruption
    -0.12
     Corruption
    -0.12
     smoothly
    -0.11
     reliably
    -0.11
     degradation
    -0.11
    Fluid
    -0.11
    -fluid
    -0.11
    POSITIVE LOGITS
     rigid
    0.16
     harsh
    0.15
     bulky
    0.14
     uncomfortable
    0.14
     overpower
    0.13
     brutal
    0.13
     unavoid
    0.12
     stiff
    0.12
     aggressive
    0.12
     rough
    0.12
    Activations Density 0.039%

    No Known Activations