© 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. 31636
    Prev
    Next
    INDEX
    Explanations

    difficult or difficulty

    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
    broker
    -0.12
    bee
    -0.11
    ight
    -0.11
    (es
    -0.11
    �t
    -0.11
    pend
    -0.11
    wards
    -0.10
    bold
    -0.10
    illa
    -0.10
    fifo
    -0.10
    POSITIVE LOGITS
    ly
    0.13
    /im
    0.12
    iek
    0.10
    icult
    0.10
    ies
    0.10
    ë¡Ŀ
    0.10
    -to
    0.09
    /fr
    0.09
    /exp
    0.09
    sand
    0.09
    Activations Density 0.031%

    No Known Activations