© 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
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26324
    Prev
    Next
    INDEX
    Explanations

    transition 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
    acos
    -0.10
    erde
    -0.09
     -
    -0.09
     however
    -0.09
     consequently
    -0.09
     –
    -0.08
     therefore
    -0.08
    ,
    -0.08
    viz
    -0.08
     metro
    -0.08
    POSITIVE LOGITS
     lul
    0.09
    reds
    0.09
    ho
    0.09
     rak
    0.09
    ughter
    0.09
     Pic
    0.09
     rhet
    0.09
    icks
    0.08
     derp
    0.08
     opaque
    0.08
    Activations Density 0.160%

    No Known Activations