© 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. 26799
    Prev
    Next
    INDEX
    Explanations

    talking about experiences

    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
     negotiations
    -0.10
     Arn
    -0.10
    oco
    -0.10
     Bold
    -0.10
     omn
    -0.09
     conducts
    -0.09
     quotation
    -0.09
     decis
    -0.09
     conduct
    -0.09
    REA
    -0.09
    POSITIVE LOGITS
     recount
    0.24
     describing
    0.22
     describe
    0.20
     divul
    0.18
     Describe
    0.18
     recounts
    0.18
     detailing
    0.18
     narr
    0.17
     talking
    0.17
     storytelling
    0.17
    Activations Density 0.088%

    No Known Activations