© 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. 14788
    Prev
    Next
    INDEX
    Explanations

    genomic signature, particle, essential, variation, method

    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
    RIX
    -0.11
     Econom
    -0.11
     rehe
    -0.10
    eve
    -0.10
    енÑĭ
    -0.10
     Wend
    -0.10
    ãģ§ãĤĤ
    -0.10
     inds
    -0.10
     âĶľ
    -0.10
    ander
    -0.10
    POSITIVE LOGITS
     alongside
    0.20
     part
    0.14
     Along
    0.11
    along
    0.11
     along
    0.11
     like
    0.11
     legitimate
    0.11
     valid
    0.10
    Along
    0.10
     tool
    0.10
    Activations Density 0.144%

    No Known Activations