© 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. 16418
    Prev
    Next
    INDEX
    Explanations

    and then / or modal verbs

    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
     pumps
    -0.09
     Sink
    -0.08
     invest
    -0.08
     Abr
    -0.08
     often
    -0.08
     Works
    -0.08
    often
    -0.08
     gras
    -0.07
     surrounded
    -0.07
     sink
    -0.07
    POSITIVE LOGITS
     should
    0.18
     shall
    0.16
     will
    0.15
     SHOULD
    0.15
    should
    0.14
     Should
    0.14
    will
    0.13
    /or
    0.13
     may
    0.13
    may
    0.12
    Activations Density 0.207%

    No Known Activations