© 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. 115274
    Prev
    Next
    INDEX
    Explanations

    py or di followed by specific words

    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
    inez
    -0.09
    eds
    -0.09
    aus
    -0.09
    sal
    -0.09
    lug
    -0.08
    IVAL
    -0.08
    elo
    -0.08
    usc
    -0.08
     assorted
    -0.08
    ering
    -0.08
    POSITIVE LOGITS
    athlon
    0.13
    dna
    0.12
    uations
    0.11
    ennial
    0.10
    ehler
    0.10
    umberland
    0.10
    lify
    0.10
    /tr
    0.10
    odus
    0.10
    rael
    0.10
    Activations Density 0.224%

    No Known Activations