© 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. 32895
    Prev
    Next
    INDEX
    Explanations

    describing how or when

    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
     gin
    -0.09
     however
    -0.09
    rais
    -0.09
    Seen
    -0.08
    seen
    -0.08
    steller
    -0.08
    ,ll
    -0.08
    avin
    -0.08
     Welch
    -0.08
     already
    -0.07
    POSITIVE LOGITS
    /or
    0.21
     chose
    0.17
     began
    0.16
     importantly
    0.15
    orra
    0.15
     took
    0.15
     vice
    0.15
     gave
    0.15
     proceeded
    0.14
    /OR
    0.14
    Activations Density 0.158%

    No Known Activations