© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 49417
    Prev
    Next
    INDEX
    Explanations

    '(token) a'

    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
     pelos
    -0.10
    unce
    -0.10
    ãģķãĤĵ
    -0.09
     *@
    -0.09
     ocur
    -0.09
     nesta
    -0.09
    iage
    -0.08
    yne
    -0.08
     giÃł
    -0.08
     olan
    -0.08
    POSITIVE LOGITS
     a
    0.36
    	a
    0.29
    _a
    0.28
    -a
    0.28
     A
    0.24
    .a
    0.23
    >a
    0.23
    *a
    0.23
    A
    0.22
    ä¸Ģ个
    0.21
    Activations Density 0.748%

    No Known Activations