© 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. 49586
    Prev
    Next
    INDEX
    Explanations

    taste and tasting

    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
    eva
    -0.10
    nee
    -0.09
    alist
    -0.09
    elles
    -0.09
     morally
    -0.09
    uko
    -0.08
     otherwise
    -0.08
     dissoci
    -0.08
    enta
    -0.08
     Diss
    -0.08
    POSITIVE LOGITS
     briefly
    0.13
     silently
    0.12
     firsthand
    0.10
    memo
    0.10
    Æ°
    0.10
     rejo
    0.10
     Moist
    0.10
     ups
    0.10
     carefully
    0.10
     sweat
    0.10
    Activations Density 0.002%

    No Known Activations