© 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. 49845
    Prev
    Next
    INDEX
    Explanations

    cutting in half

    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
     crem
    -0.11
    ĥģ
    -0.09
     Brushes
    -0.09
    -record
    -0.09
    arten
    -0.08
     gifts
    -0.08
     Bounty
    -0.08
     Nur
    -0.08
    ikan
    -0.08
     oral
    -0.08
    POSITIVE LOGITS
    Cut
    0.26
     cutting
    0.25
    cut
    0.25
    =cut
    0.25
     cut
    0.25
     Cutting
    0.25
     Cut
    0.24
     cuts
    0.24
    cuts
    0.22
     CUT
    0.22
    Activations Density 0.292%

    No Known Activations