© 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. 33154
    Prev
    Next
    INDEX
    Explanations

    however, article, work

    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
    -esque
    -0.15
     obsc
    -0.15
     egregious
    -0.14
     overarching
    -0.14
    —or
    -0.13
     historically
    -0.13
     disproportionately
    -0.13
     arguably
    -0.13
     foundational
    -0.13
    —including
    -0.12
    POSITIVE LOGITS
     firstly
    0.19
     envis
    0.17
     reputed
    0.17
     duly
    0.17
    Apart
    0.16
     Apart
    0.16
     equipments
    0.16
     nowadays
    0.16
     learnt
    0.15
    Moreover
    0.15
    Activations Density 0.023%

    No Known Activations