© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5824
    Prev
    Next
    INDEX
    Explanations

    hap, apt, haploid, haptoglobin

    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
     Vit
    -0.11
     cub
    -0.10
    ernity
    -0.09
     dul
    -0.09
    dana
    -0.09
    ifr
    -0.09
     Eins
    -0.09
    azioni
    -0.08
    ATOR
    -0.08
    anut
    -0.08
    POSITIVE LOGITS
     hap
    0.14
    lessly
    0.13
    hap
    0.11
    azard
    0.11
     spont
    0.10
     coded
    0.10
     happ
    0.10
     unlucky
    0.10
    antu
    0.09
    lobal
    0.09
    Activations Density 0.016%

    No Known Activations