© 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. 47858
    Prev
    Next
    INDEX
    Explanations

    secretary general

    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
    ede
    -0.10
     Hop
    -0.10
     Stra
    -0.09
     uncovered
    -0.09
     bef
    -0.08
     EVER
    -0.08
    orig
    -0.08
     Deutsch
    -0.08
     McCorm
    -0.08
     Alla
    -0.08
    POSITIVE LOGITS
     thoughts
    0.28
     Responses
    0.27
     Comments
    0.26
    Comments
    0.25
    Leave
    0.24
     comments
    0.23
     Replies
    0.23
     responses
    0.23
     Comment
    0.21
     Response
    0.21
    Activations Density 0.174%

    No Known Activations