© 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. 48375
    Prev
    Next
    INDEX
    Explanations

    matter

    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
     Majority
    -0.10
    vak
    -0.10
    ery
    -0.09
    lex
    -0.09
    anity
    -0.09
    hti
    -0.09
    abor
    -0.08
    etta
    -0.08
    eca
    -0.08
    estruct
    -0.08
    POSITIVE LOGITS
    iale
    0.15
    ials
    0.15
    uala
    0.11
    horn
    0.11
    -of
    0.11
     fact
    0.10
    edList
    0.10
    ial
    0.10
     worse
    0.10
     Worse
    0.10
    Activations Density 0.035%

    No Known Activations