© 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. 89802
    Prev
    Next
    INDEX
    Explanations

    proposition or propositions

    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
    ates
    -0.12
    elves
    -0.11
    ogue
    -0.10
    upa
    -0.10
     anomal
    -0.10
    imeter
    -0.10
     Leslie
    -0.09
    kle
    -0.09
     indo
    -0.09
    COPY
    -0.09
    POSITIVE LOGITS
    ing
    0.21
    ed
    0.14
     propositions
    0.13
    sWith
    0.12
    ING
    0.11
     proposition
    0.11
    edBy
    0.10
    ilan
    0.09
    ingly
    0.09
    /pro
    0.09
    Activations Density 0.002%

    No Known Activations