© 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. 47931
    Prev
    Next
    INDEX
    Explanations

    way to do something

    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
    ever
    -0.12
     ever
    -0.10
    iman
    -0.10
    eln
    -0.10
    DMA
    -0.09
    uid
    -0.09
     all
    -0.09
    invert
    -0.09
    acker
    -0.09
     guides
    -0.09
    POSITIVE LOGITS
     contributing
    0.12
     frequently
    0.12
     besides
    0.12
     commonly
    0.11
     prominently
    0.10
     tess
    0.09
     Sequ
    0.09
     cited
    0.09
     intens
    0.09
    Alias
    0.09
    Activations Density 0.244%

    No Known Activations