© 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. 33972
    Prev
    Next
    INDEX
    Explanations

    had crafted something

    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
    atus
    -0.12
    dy
    -0.11
     Clips
    -0.11
    ulet
    -0.10
     Bits
    -0.10
     taxing
    -0.10
    rend
    -0.10
    cio
    -0.09
     quota
    -0.09
     Pell
    -0.09
    POSITIVE LOGITS
     witnessing
    0.17
     witnessed
    0.16
     stumbled
    0.15
     witness
    0.14
     found
    0.14
     hit
    0.13
     here
    0.13
     Witness
    0.12
     unwitting
    0.12
     winner
    0.12
    Activations Density 0.250%

    No Known Activations