© 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. 115077
    Prev
    Next
    INDEX
    Explanations

    do you

    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
    did
    -0.13
     did
    -0.11
    Fo
    -0.10
    Did
    -0.09
     Did
    -0.09
    ides
    -0.09
    IRD
    -0.09
     gdb
    -0.09
    ULO
    -0.09
    ship
    -0.09
    POSITIVE LOGITS
     perman
    0.10
     Buch
    0.09
    oter
    0.09
    owi
    0.09
    yen
    0.09
     cher
    0.09
     stagger
    0.08
    /do
    0.08
     Bucc
    0.08
     anim
    0.08
    Activations Density 0.006%

    No Known Activations