© 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. 90834
    Prev
    Next
    INDEX
    Explanations

    short and concise outputs

    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
     alone
    -0.12
    alone
    -0.11
     Alone
    -0.09
    mil
    -0.09
     unconventional
    -0.09
     Neville
    -0.09
     setC
    -0.09
     Sne
    -0.09
    lon
    -0.09
    uto
    -0.09
    POSITIVE LOGITS
     concise
    0.26
     succinct
    0.23
     cond
    0.22
     condensed
    0.22
     bre
    0.20
     Cond
    0.19
     shorter
    0.18
     streamlined
    0.18
     shorten
    0.17
    Cond
    0.17
    Activations Density 0.241%

    No Known Activations