© 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. 18506
    Prev
    Next
    INDEX
    Explanations

    unique and unusual traits

    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
     slime
    -0.11
     aprove
    -0.10
     pulver
    -0.10
    ething
    -0.10
    lam
    -0.10
    ardy
    -0.10
     disgusted
    -0.10
    über
    -0.10
    eren
    -0.10
    ibili
    -0.09
    POSITIVE LOGITS
     quirky
    0.33
     eccentric
    0.31
     quir
    0.29
     odd
    0.21
     whims
    0.21
     peculiar
    0.20
    quir
    0.19
     quaint
    0.19
     charming
    0.18
     eclectic
    0.18
    Activations Density 0.039%

    No Known Activations