© 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. 47333
    Prev
    Next
    INDEX
    Explanations

    hear opinions and feedback

    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
     Retreat
    -0.10
     PROVID
    -0.10
     slack
    -0.10
    serv
    -0.09
     extrem
    -0.09
     dint
    -0.09
    antal
    -0.09
     informing
    -0.09
     incred
    -0.09
    Prov
    -0.09
    POSITIVE LOGITS
     stories
    0.14
     about
    0.13
     story
    0.11
     excuses
    0.11
     opinions
    0.11
     justification
    0.11
    stories
    0.11
     how
    0.10
     feedback
    0.09
    iot
    0.09
    Activations Density 0.012%

    No Known Activations