© 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. 13855
    Prev
    Next
    INDEX
    Explanations

    fang and tusks

    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
     Alive
    -0.11
     hoof
    -0.11
     Hands
    -0.11
     Fist
    -0.10
     sid
    -0.10
    -eye
    -0.10
     Stamp
    -0.10
    Stamp
    -0.10
     Coordinates
    -0.10
     frozen
    -0.10
    POSITIVE LOGITS
     retract
    0.17
     protr
    0.13
     sharp
    0.12
     piercing
    0.10
     sharpen
    0.10
     sharper
    0.10
    length
    0.09
     lengths
    0.09
     replacements
    0.09
    sharp
    0.09
    Activations Density 0.005%

    No Known Activations