© 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. 31763
    Prev
    Next
    INDEX
    Explanations

    frequency per time period

    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
     Dawn
    -0.12
    exo
    -0.11
    .xyz
    -0.10
    VA
    -0.10
     Dest
    -0.10
    SI
    -0.10
    -time
    -0.10
    ÑģÑı
    -0.10
     Rem
    -0.10
    cot
    -0.10
    POSITIVE LOGITS
     per
    0.12
     week
    0.11
     day
    0.10
    lix
    0.10
     Flynn
    0.09
    /day
    0.09
     marque
    0.09
     weekday
    0.09
    -a
    0.08
    _per
    0.08
    Activations Density 0.040%

    No Known Activations