© 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. 112571
    Prev
    Next
    INDEX
    Explanations

    Nick comments, Bill’s, I know

    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
    ibri
    -0.08
     assum
    -0.08
     crashed
    -0.08
     charismatic
    -0.07
    inary
    -0.07
     plung
    -0.07
     binary
    -0.07
     sync
    -0.07
     apolog
    -0.07
     kissed
    -0.07
    POSITIVE LOGITS
     watched
    0.21
     watching
    0.21
     watch
    0.21
    watch
    0.20
     watches
    0.19
     WATCH
    0.18
     intervene
    0.17
     Watch
    0.17
     Watching
    0.16
     intervention
    0.16
    Activations Density 0.090%

    No Known Activations