© 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. 113457
    Prev
    Next
    INDEX
    Explanations

    IP addresses

    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
     sac
    -0.12
    pler
    -0.10
     stale
    -0.09
    erek
    -0.09
     dalle
    -0.08
    ì¦
    -0.08
    indi
    -0.08
     schn
    -0.08
     Quit
    -0.08
    erk
    -0.08
    POSITIVE LOGITS
    254
    0.17
    255
    0.16
    168
    0.15
    253
    0.14
     IPs
    0.14
    249
    0.14
    248
    0.13
     IP
    0.13
    219
    0.13
    172
    0.13
    Activations Density 0.144%

    No Known Activations