© 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. 116106
    Prev
    Next
    INDEX
    Explanations

    without penalty or issues

    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
     Pub
    -0.10
     impro
    -0.10
     lawy
    -0.10
     ruth
    -0.10
    æ´
    -0.10
     delic
    -0.10
    aben
    -0.10
     Require
    -0.10
    PK
    -0.10
     catast
    -0.10
    POSITIVE LOGITS
     worry
    0.22
     interruption
    0.21
     interruptions
    0.21
     worrying
    0.21
     interference
    0.20
     fear
    0.20
     worries
    0.17
     Fear
    0.16
     interrupted
    0.16
     fearing
    0.15
    Activations Density 0.019%

    No Known Activations