© 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. 17728
    Prev
    Next
    INDEX
    Explanations

    qualification or qualifies

    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
     Wo
    -0.09
    -connect
    -0.09
     occasional
    -0.08
     Signing
    -0.08
     pled
    -0.08
     Paleo
    -0.08
     chances
    -0.08
    cean
    -0.08
    ector
    -0.08
     Membership
    -0.08
    POSITIVE LOGITS
    infra
    0.10
    enk
    0.09
    asan
    0.09
     Barber
    0.09
     Bair
    0.09
    ä¼
    0.09
    roph
    0.08
     indirectly
    0.08
    .kr
    0.08
    Ñİ
    0.08
    Activations Density 0.144%

    No Known Activations