© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 111599
    Prev
    Next
    INDEX
    Explanations

    mesosphere

    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
    Negative Logits
    filer
    -0.11
    itoris
    -0.10
    orra
    -0.10
    олÑĮз
    -0.10
     calle
    -0.10
     Cah
    -0.09
     shutting
    -0.09
     Herman
    -0.09
    UED
    -0.09
    ARTH
    -0.09
    POSITIVE LOGITS
    оÑģÑĮ
    0.11
    eler
    0.09
     Jam
    0.09
     pity
    0.09
    offers
    0.09
    åĬ¡
    0.09
    o
    0.09
    ials
    0.09
    jon
    0.08
     Homepage
    0.08
    Activations Density 0.001%

    No Known Activations