© 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. 6083
    Prev
    Next
    INDEX
    Explanations

    the + noun

    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
     remainder
    -0.11
     admittedly
    -0.10
    uge
    -0.10
     beginnings
    -0.10
     backs
    -0.09
    aye
    -0.09
     Legislature
    -0.09
    aa
    -0.09
     dozen
    -0.08
     bef
    -0.08
    POSITIVE LOGITS
     said
    0.21
     concerned
    0.19
    said
    0.17
     academia
    0.13
     motive
    0.13
     moot
    0.13
     society
    0.13
     looph
    0.12
     awaited
    0.12
     Said
    0.12
    Activations Density 0.800%

    No Known Activations