© 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. 48178
    Prev
    Next
    INDEX
    Explanations

    1612-1613 or 1810s

    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
    ibus
    -0.10
    ibe
    -0.09
    ths
    -0.09
    iations
    -0.09
    nelly
    -0.08
    gue
    -0.08
    lds
    -0.08
     neat
    -0.08
    icht
    -0.08
    loi
    -0.08
    POSITIVE LOGITS
    st
    0.34
    sti
    0.14
    stin
    0.13
    sts
    0.12
    ****************************
    0.12
    /XMLSchema
    0.11
    sto
    0.11
    stro
    0.11
    ÑģÑĤ
    0.11
    stag
    0.11
    Activations Density 0.362%

    No Known Activations