© 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. 25417
    Prev
    Next
    INDEX
    Explanations

    fulfilling goals and obligations

    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
     Thema
    -0.10
     sight
    -0.10
     wheels
    -0.09
     Fits
    -0.09
    RTL
    -0.09
     Xin
    -0.09
     fingerprints
    -0.09
    éĹ®é¢ĺ
    -0.09
    rase
    -0.09
    UCT
    -0.09
    POSITIVE LOGITS
     promise
    0.23
     promises
    0.22
     dreams
    0.20
     prophecy
    0.20
     obligations
    0.18
     destiny
    0.18
     duties
    0.17
     fantasies
    0.17
     quota
    0.17
     obligation
    0.16
    Activations Density 0.020%

    No Known Activations