© 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. 15271
    Prev
    Next
    INDEX
    Explanations

    need proof or assistance

    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
     uphold
    -0.11
     Nug
    -0.11
    ahi
    -0.11
     Madd
    -0.11
    logo
    -0.10
     Sep
    -0.10
    Ix
    -0.10
    menus
    -0.10
    reverse
    -0.10
    542
    -0.10
    POSITIVE LOGITS
     convinced
    0.26
     doubt
    0.25
     doub
    0.24
     Doub
    0.24
     still
    0.23
     STILL
    0.23
     doubts
    0.22
     skeptical
    0.22
    Still
    0.22
     Still
    0.21
    Activations Density 0.074%

    No Known Activations