© 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. 28568
    Prev
    Next
    INDEX
    Explanations

    if you

    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
    arp
    -0.08
    odos
    -0.08
    ın
    -0.08
    asel
    -0.08
     cal
    -0.08
    ár
    -0.08
     Swe
    -0.08
    ìļ´
    -0.08
    ais
    -0.08
    228
    -0.07
    POSITIVE LOGITS
     anything
    0.64
    anything
    0.51
     Anything
    0.49
    Anything
    0.44
     nothing
    0.19
     NOTHING
    0.17
     rien
    0.16
     everything
    0.15
    nothing
    0.15
     anywhere
    0.15
    Activations Density 0.092%

    No Known Activations