© 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. 32507
    Prev
    Next
    INDEX
    Explanations

    saban said, the Massachusetts, invention relates

    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
     frowned
    -0.11
     angrily
    -0.10
     thru
    -0.10
     secretly
    -0.09
     terrified
    -0.09
     whilst
    -0.09
     wealthy
    -0.09
     slowly
    -0.09
     HUGE
    -0.09
     atleast
    -0.09
    POSITIVE LOGITS
    cura
    0.10
     seeming
    0.10
     particulars
    0.10
     unmistak
    0.10
     comple
    0.10
     unavoid
    0.10
     very
    0.10
     Klein
    0.09
     whatever
    0.09
     undone
    0.09
    Activations Density 0.294%

    No Known Activations