© 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. 88752
    Prev
    Next
    INDEX
    Explanations

    locations and opportunities

    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
     unus
    -0.10
    legg
    -0.10
     punitive
    -0.10
    /terms
    -0.09
     wikipedia
    -0.09
    omba
    -0.09
     pn
    -0.09
    pun
    -0.09
     childhood
    -0.09
    intr
    -0.09
    POSITIVE LOGITS
     frequ
    0.17
     attracts
    0.17
     opportunities
    0.16
     populated
    0.16
     chances
    0.16
     ming
    0.15
     likelihood
    0.15
     fertile
    0.15
     Opportunities
    0.15
     plentiful
    0.14
    Activations Density 0.054%

    No Known Activations