© 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. 90547
    Prev
    Next
    INDEX
    Explanations

    alternatives or choices

    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
     consequ
    -0.11
    pii
    -0.10
     unintention
    -0.10
    prevent
    -0.10
     inevitable
    -0.10
    /Dk
    -0.10
     ctxt
    -0.10
    ophile
    -0.10
     unknow
    -0.10
    –and
    -0.10
    POSITIVE LOGITS
     alternatively
    0.21
     preferably
    0.19
     equivalent
    0.19
     equival
    0.16
     Equivalent
    0.15
     equivalents
    0.13
    ients
    0.13
     directly
    0.12
     whichever
    0.12
     whatever
    0.12
    Activations Density 0.295%

    No Known Activations