© 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. 33010
    Prev
    Next
    INDEX
    Explanations

    ejection from

    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
     Hur
    -0.11
     tou
    -0.11
    /options
    -0.11
    mente
    -0.10
     Taste
    -0.10
    ICE
    -0.10
    enis
    -0.10
     bouts
    -0.09
     tast
    -0.09
     abruptly
    -0.09
    POSITIVE LOGITS
     slowly
    0.13
     forth
    0.11
     out
    0.11
     oo
    0.10
    -out
    0.10
     heraus
    0.10
     propriet
    0.09
     into
    0.09
     lava
    0.09
     gradu
    0.09
    Activations Density 0.003%

    No Known Activations