© 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. 48145
    Prev
    Next
    INDEX
    Explanations

    casually commenting or realizing

    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
     perhaps
    -0.10
     anyhow
    -0.10
     Tin
    -0.09
    perhaps
    -0.08
    !I
    -0.08
    Perhaps
    -0.08
     Tues
    -0.08
     secre
    -0.08
     Perhaps
    -0.08
    ickey
    -0.08
    POSITIVE LOGITS
     literally
    0.16
     everytime
    0.14
     genuinely
    0.14
     casually
    0.14
     whenever
    0.14
     legitimately
    0.13
     realizing
    0.13
     rl
    0.12
    ....↵↵
    0.12
     mf
    0.12
    Activations Density 0.160%

    No Known Activations