© 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. 114225
    Prev
    Next
    INDEX
    Explanations

    conjunctions (and, but)

    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
    uche
    -0.11
    rint
    -0.11
     inters
    -0.11
     tantra
    -0.10
     Erf
    -0.10
    cis
    -0.10
    acia
    -0.10
     zest
    -0.10
    ischer
    -0.10
     Tantra
    -0.10
    POSITIVE LOGITS
     nonexistent
    0.10
     otherwise
    0.09
     differently
    0.09
     Cha
    0.08
     anders
    0.08
     separately
    0.08
    _io
    0.08
    iska
    0.08
     absent
    0.07
    spm
    0.07
    Activations Density 0.841%

    No Known Activations