© 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. 113461
    Prev
    Next
    INDEX
    Explanations

    about specific purchases

    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
    inel
    -0.10
    RS
    -0.10
     Aer
    -0.10
    irty
    -0.09
    asan
    -0.09
    hel
    -0.09
     Kel
    -0.09
    unsch
    -0.08
    ún
    -0.08
    elen
    -0.08
    POSITIVE LOGITS
    åĪĻ
    0.14
    ï¼ĮåĪĻ
    0.13
     Rubio
    0.12
     then
    0.12
     THEN
    0.11
    	then
    0.11
    then
    0.10
     entonces
    0.10
     maka
    0.10
    è¯Ŀ
    0.10
    Activations Density 0.098%

    No Known Activations