© 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. 8328
    Prev
    Next
    INDEX
    Explanations

    bl starts words referring to specific concepts like names or medical conditions

    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
    rior
    -0.09
    apol
    -0.09
    semb
    -0.09
    apon
    -0.08
    edom
    -0.08
    oret
    -0.08
    ular
    -0.08
    imas
    -0.08
    pires
    -0.08
    atel
    -0.08
    POSITIVE LOGITS
    /bl
    0.18
     Blind
    0.17
     Blanco
    0.17
     blur
    0.16
    -bl
    0.15
    .Bl
    0.15
     blurred
    0.15
     bla
    0.15
     Blanch
    0.15
     Blend
    0.15
    Activations Density 0.019%

    No Known Activations