© 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. 46807
    Prev
    Next
    INDEX
    Explanations

    Monthly Archives

    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
    unk
    -0.08
    TAG
    -0.08
     sure
    -0.08
     recommendation
    -0.08
    æ¯
    -0.07
     vic
    -0.07
    addy
    -0.07
     Commons
    -0.07
     cuck
    -0.07
    LAG
    -0.07
    POSITIVE LOGITS
     ipc
    0.12
     negotiating
    0.11
     Prot
    0.10
     replay
    0.10
    etat
    0.10
    ı
    0.10
     Decor
    0.10
     Barker
    0.09
     Protocol
    0.09
     Diss
    0.09
    Activations Density 0.001%

    No Known Activations