© 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. 49407
    Prev
    Next
    INDEX
    Explanations

    each week or year

    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
     yearly
    -0.18
     occasional
    -0.17
     annual
    -0.16
     occasionally
    -0.13
     Annual
    -0.12
     monthly
    -0.12
     annually
    -0.12
    Annual
    -0.11
     continually
    -0.10
     continuous
    -0.10
    POSITIVE LOGITS
     anew
    0.13
    dm
    0.11
     Kear
    0.10
     ritual
    0.10
     bek
    0.10
     dut
    0.10
     Renew
    0.10
     foregoing
    0.10
     dilemma
    0.09
    ож
    0.09
    Activations Density 0.077%

    No Known Activations