© 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. 48142
    Prev
    Next
    INDEX
    Explanations

    pinch of salt

    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
     genuinely
    -0.12
     legitimately
    -0.12
     legit
    -0.11
    imon
    -0.11
     legitim
    -0.11
     brave
    -0.11
     bravery
    -0.11
     Mess
    -0.11
     misc
    -0.11
    ulled
    -0.11
    POSITIVE LOGITS
     grain
    0.13
     salt
    0.12
     pinch
    0.10
     caveat
    0.10
     Salt
    0.10
     icing
    0.10
     Grain
    0.10
     grains
    0.10
     tongue
    0.09
     pound
    0.09
    Activations Density 0.018%

    No Known Activations