© 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. 112728
    Prev
    Next
    INDEX
    Explanations

    genome sequences

    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
     Cro
    -0.11
     fict
    -0.10
     dart
    -0.10
    Cro
    -0.09
     cre
    -0.09
     Hou
    -0.09
     Emm
    -0.08
     improvised
    -0.08
    nh
    -0.08
    -other
    -0.08
    POSITIVE LOGITS
    cue
    0.10
     Clash
    0.10
    cape
    0.10
     hopeless
    0.09
     clash
    0.09
    ety
    0.09
    eland
    0.09
     prefect
    0.09
     outgoing
    0.09
    365
    0.09
    Activations Density 0.008%

    No Known Activations