© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 47998
    Prev
    Next
    INDEX
    Explanations

    dialogue punctuation

    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
    umeric
    -0.12
     stare
    -0.11
    ording
    -0.11
    ddl
    -0.11
    INLINE
    -0.11
     positives
    -0.11
    auc
    -0.11
     pus
    -0.11
    coop
    -0.10
     psychologically
    -0.10
    POSITIVE LOGITS
     chor
    0.12
     chorus
    0.12
     interchange
    0.11
     various
    0.09
     clutter
    0.08
     bored
    0.08
     Bryant
    0.08
     reply
    0.08
     echo
    0.07
    oton
    0.07
    Activations Density 0.001%

    No Known Activations