© 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. 17206
    Prev
    Next
    INDEX
    Explanations

    apologizing for mistakes

    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
    iaux
    -0.10
    avirus
    -0.10
     Runner
    -0.09
     Spit
    -0.09
     IMO
    -0.09
    tz
    -0.09
     reconsider
    -0.09
     typ
    -0.09
    ramework
    -0.08
     undecided
    -0.08
    POSITIVE LOGITS
     seeming
    0.24
     seemingly
    0.22
     occasionally
    0.16
     appearing
    0.16
     sometimes
    0.16
     abruptly
    0.16
     suddenly
    0.15
     apparent
    0.15
     appearances
    0.15
     sounding
    0.14
    Activations Density 0.248%

    No Known Activations