© 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. 112330
    Prev
    Next
    INDEX
    Explanations

    foreign sounding names and places

    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
    istics
    -0.10
    eger
    -0.10
    eft
    -0.10
     compressed
    -0.10
    bij
    -0.09
     chr
    -0.09
     breat
    -0.09
    ÃŃst
    -0.09
     compress
    -0.09
     deduct
    -0.09
    POSITIVE LOGITS
    gran
    0.08
     Off
    0.08
     Gord
    0.08
     Lond
    0.08
     Rubin
    0.08
     hass
    0.08
    jian
    0.08
     Cum
    0.08
     halfway
    0.08
     sustain
    0.08
    Activations Density 0.002%

    No Known Activations