© 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. 30993
    Prev
    Next
    INDEX
    Explanations

    responding to yes/no questions

    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
     Stephens
    -0.10
    oris
    -0.10
    /send
    -0.10
     unserialize
    -0.10
     Burl
    -0.09
     verge
    -0.09
     prefect
    -0.09
     Ramos
    -0.09
     Sender
    -0.09
    ghi
    -0.09
    POSITIVE LOGITS
     "
    0.17
     “
    0.15
     yes
    0.14
     "...
    0.13
     “âĢ¦
    0.13
     smile
    0.12
     nod
    0.11
     Yes
    0.11
    :
    0.11
     “[
    0.11
    Activations Density 0.040%

    No Known Activations