© 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. 49924
    Prev
    Next
    INDEX
    Explanations

    designed, established, drug

    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
     had
    -0.15
     habÃŃa
    -0.14
     was
    -0.13
    was
    -0.13
    _was
    -0.13
    had
    -0.13
    etti
    -0.13
     began
    -0.13
     gave
    -0.12
     drew
    -0.12
    POSITIVE LOGITS
     hasn
    0.09
    aris
    0.09
     feels
    0.08
     interv
    0.08
     Considering
    0.08
    eli
    0.07
     isn
    0.07
     appart
    0.07
     has
    0.07
     now
    0.07
    Activations Density 0.093%

    No Known Activations