© 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. 89686
    Prev
    Next
    INDEX
    Explanations

    appearances and presentations

    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
    ento
    -0.11
     derivatives
    -0.10
    quent
    -0.10
    nev
    -0.10
    nel
    -0.10
     Nov
    -0.09
     Cher
    -0.09
     effected
    -0.09
     Donne
    -0.09
    eci
    -0.09
    POSITIVE LOGITS
     Hint
    0.10
    aro
    0.09
     shocking
    0.09
     coerc
    0.08
    unal
    0.08
     Appeal
    0.08
     Paula
    0.08
     Dominic
    0.07
     hint
    0.07
     rare
    0.07
    Activations Density 0.076%

    No Known Activations