© 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. 32941
    Prev
    Next
    INDEX
    Explanations

    raise concerns or topics

    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
    ubs
    -0.12
    ogi
    -0.10
    endor
    -0.10
     scoop
    -0.10
    _capability
    -0.10
     wink
    -0.09
     substituted
    -0.09
     contemplated
    -0.09
     chill
    -0.09
    malink
    -0.09
    POSITIVE LOGITS
     concerns
    0.14
     topic
    0.14
     conversation
    0.13
     issues
    0.12
     topics
    0.12
     issue
    0.12
     Topics
    0.12
     Concern
    0.12
    /topic
    0.11
    /question
    0.11
    Activations Density 0.020%

    No Known Activations