© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14570
    Prev
    Next
    INDEX
    Explanations

    so that I can

    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
    Not in Any Lists

    No Comments

    Negative Logits
    now
    -0.11
     fos
    -0.10
    doll
    -0.10
     fils
    -0.10
     Gund
    -0.09
    hausen
    -0.09
    fos
    -0.09
    andi
    -0.09
    rab
    -0.09
    .now
    -0.09
    POSITIVE LOGITS
     properly
    0.14
     truly
    0.11
     Proper
    0.11
     proper
    0.10
    344
    0.10
     relief
    0.10
    errer
    0.10
     unc
    0.10
    emb
    0.10
     pret
    0.09
    Activations Density 0.040%

    No Known Activations