© 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. 47486
    Prev
    Next
    INDEX
    Explanations

    phrases ending with punctuation or conjunctions

    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
    aland
    -0.10
     suitable
    -0.10
    PTS
    -0.09
     wah
    -0.09
    EEE
    -0.09
    wright
    -0.09
    nev
    -0.09
    accom
    -0.09
     Gund
    -0.09
     gentle
    -0.09
    POSITIVE LOGITS
     Lif
    0.09
     pristine
    0.09
    SEQ
    0.09
     nasty
    0.09
     Extras
    0.09
     infr
    0.08
     nast
    0.08
     lif
    0.08
    onus
    0.08
     awe
    0.08
    Activations Density 0.001%

    No Known Activations