© 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. 27291
    Prev
    Next
    INDEX
    Explanations

    possession, statements, facts, or data

    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
     Prev
    -0.10
    Prev
    -0.10
    Fallback
    -0.09
    ãģŁãģł
    -0.09
     promin
    -0.09
     Prest
    -0.08
    Mutable
    -0.08
    cord
    -0.08
     Watt
    -0.08
    (kind
    -0.08
    POSITIVE LOGITS
     UR
    0.11
    APA
    0.11
     insult
    0.10
     crossword
    0.10
     gossip
    0.09
     mish
    0.09
     Box
    0.09
     box
    0.09
     inj
    0.09
     sarc
    0.09
    Activations Density 0.034%

    No Known Activations