© 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. 88383
    Prev
    Next
    INDEX
    Explanations

    whatever, regardless, anyway

    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
    illo
    -0.12
    atin
    -0.11
     suit
    -0.11
    idis
    -0.10
    (strict
    -0.10
    acco
    -0.10
    nof
    -0.10
    trx
    -0.10
    ritt
    -0.10
     suits
    -0.10
    POSITIVE LOGITS
     whatever
    0.34
     Whatever
    0.34
    Whatever
    0.32
     Regardless
    0.32
     regardless
    0.31
    Regardless
    0.30
    whatever
    0.28
     anyhow
    0.24
     anyway
    0.22
     irrespective
    0.20
    Activations Density 0.104%

    No Known Activations