© 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. 31089
    Prev
    Next
    INDEX
    Explanations

    XML/YAML/Schema definitions

    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
    -/
    -0.09
     Fletcher
    -0.09
     fronts
    -0.09
    _folders
    -0.09
     unb
    -0.09
     bott
    -0.08
     *&
    -0.08
    Front
    -0.08
     Connections
    -0.08
     Ebony
    -0.08
    POSITIVE LOGITS
    CDATA
    0.16
     urn
    0.15
     xmlns
    0.14
    rdf
    0.14
     RDF
    0.13
    .rdf
    0.13
     rdf
    0.12
     xsi
    0.12
     xlink
    0.12
     minOccurs
    0.11
    Activations Density 6.379%

    No Known Activations