© 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. 18083
    Prev
    Next
    INDEX
    Explanations

    last occurrences

    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
     early
    -0.15
     dawn
    -0.13
     Early
    -0.13
     morning
    -0.13
     sunrise
    -0.13
     Morning
    -0.13
    early
    -0.12
    Early
    -0.12
    ajo
    -0.12
     beforehand
    -0.11
    POSITIVE LOGITS
     last
    0.15
     LAST
    0.14
    .last
    0.14
    last
    0.13
    LAST
    0.13
     getLast
    0.12
     late
    0.12
    [last
    0.11
     Last
    0.11
    >Last
    0.11
    Activations Density 0.144%

    No Known Activations