© 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. 33295
    Prev
    Next
    INDEX
    Explanations

    proof and verification

    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
    fy
    -0.10
     hopeful
    -0.10
    hol
    -0.10
     deserves
    -0.10
    ager
    -0.10
     bothering
    -0.10
     kennen
    -0.10
     Reception
    -0.10
     keynote
    -0.09
    /qt
    -0.09
    POSITIVE LOGITS
     proving
    0.24
     proof
    0.22
     prove
    0.21
     verification
    0.21
     proves
    0.19
     verifying
    0.19
     Verification
    0.18
    è¯ģ
    0.18
     Proof
    0.18
     proofs
    0.17
    Activations Density 0.124%

    No Known Activations