© 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. 47981
    Prev
    Next
    INDEX
    Explanations

    School served published

    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
     dry
    -0.10
     Kenya
    -0.09
     mercy
    -0.09
     Virt
    -0.08
     Sob
    -0.08
    izi
    -0.08
     hydrated
    -0.08
     Mercy
    -0.08
     Dict
    -0.08
     Soft
    -0.08
    POSITIVE LOGITS
    eks
    0.11
     lib
    0.10
     aff
    0.10
     le
    0.10
    aste
    0.10
    atif
    0.09
    rlen
    0.09
    astes
    0.09
     Isaac
    0.09
     hic
    0.09
    Activations Density 0.006%

    No Known Activations