© 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. 5871
    Prev
    Next
    INDEX
    Explanations

    licensing and copyright notices

    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
     Boyle
    -0.08
    Sites
    -0.08
     grav
    -0.08
     Helen
    -0.08
     soft
    -0.08
     touched
    -0.08
     mixes
    -0.07
    -pt
    -0.07
    eric
    -0.07
     Kendrick
    -0.07
    POSITIVE LOGITS
     fut
    0.10
     Logged
    0.10
     Mata
    0.10
     pong
    0.10
     Sans
    0.10
     Bing
    0.10
    Deque
    0.10
     tat
    0.09
     Ingen
    0.09
     ims
    0.09
    Activations Density 0.007%

    No Known Activations