© 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. 6461
    Prev
    Next
    INDEX
    Explanations

    identifying and characterizing substances

    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
    icl
    -0.13
     hott
    -0.10
     passer
    -0.10
    pta
    -0.10
    /story
    -0.09
    alte
    -0.09
    tid
    -0.09
    ungle
    -0.09
     prow
    -0.09
     MISSING
    -0.09
    POSITIVE LOGITS
     resembled
    0.14
     consisted
    0.13
     resembles
    0.13
     resemble
    0.12
     consisting
    0.12
     consists
    0.12
     whatever
    0.12
     revealed
    0.12
     what
    0.11
    —a
    0.11
    Activations Density 0.131%

    No Known Activations