© 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. 4478
    Prev
    Next
    INDEX
    Explanations

    tasked/charged with

    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
     grues
    -0.11
    mi
    -0.11
    enson
    -0.10
    deo
    -0.10
    arp
    -0.10
     Concord
    -0.10
    Eb
    -0.10
     nail
    -0.10
    umble
    -0.10
    ARP
    -0.10
    POSITIVE LOGITS
     with
    0.19
    with
    0.14
    	with
    0.13
     avec
    0.12
     With
    0.12
    _with
    0.11
    avec
    0.11
    ewith
    0.10
    atat
    0.10
     dengan
    0.10
    Activations Density 0.082%

    No Known Activations