© 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. 89653
    Prev
    Next
    INDEX
    Explanations

    especially plentiful

    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
     thereby
    -0.11
    idge
    -0.11
     therefore
    -0.11
    ertz
    -0.10
    ilo
    -0.10
     violating
    -0.10
     consequently
    -0.09
     Wants
    -0.09
     thus
    -0.09
    oten
    -0.09
    POSITIVE LOGITS
     especially
    0.11
     Especially
    0.11
     discre
    0.11
    especially
    0.10
     Plenty
    0.10
     combines
    0.10
     Firstly
    0.10
     abund
    0.09
     caveat
    0.09
     abundant
    0.09
    Activations Density 0.246%

    No Known Activations