© 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. 116061
    Prev
    Next
    INDEX
    Explanations

    names starting with "Ar"

    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
    atto
    -0.10
     Crack
    -0.10
    indi
    -0.10
     reun
    -0.09
    ocus
    -0.09
     effected
    -0.09
    affected
    -0.09
    isser
    -0.09
     Mor
    -0.09
     ann
    -0.09
    POSITIVE LOGITS
    uards
    0.08
    hed
    0.08
    guards
    0.08
     leaning
    0.08
     backdrop
    0.08
     outright
    0.08
    Hospital
    0.08
    raz
    0.08
     inclination
    0.08
     angled
    0.08
    Activations Density 0.003%

    No Known Activations