© 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. 28378
    Prev
    Next
    INDEX
    Explanations

    held long enough

    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
    cie
    -0.11
    udo
    -0.11
    udes
    -0.10
    TY
    -0.10
     Trap
    -0.10
    uto
    -0.10
     autos
    -0.10
     stren
    -0.10
     Hut
    -0.10
    pivot
    -0.10
    POSITIVE LOGITS
     anymore
    0.32
     longer
    0.14
     finally
    0.14
    finally
    0.12
     forever
    0.12
     restraint
    0.11
     Longer
    0.10
     conceal
    0.10
     wait
    0.10
     succ
    0.09
    Activations Density 0.015%

    No Known Activations