© 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. 91645
    Prev
    Next
    INDEX
    Explanations

    firmware or licensing

    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
    æĹ
    -0.11
    uela
    -0.11
    ahl
    -0.10
     Narr
    -0.10
    endid
    -0.09
    amina
    -0.09
    others
    -0.09
    hausen
    -0.09
    rlen
    -0.09
    appe
    -0.09
    POSITIVE LOGITS
     fir
    0.09
    -assets
    0.09
     those
    0.09
    iert
    0.08
    /run
    0.08
     Horny
    0.08
     forcibly
    0.08
     firm
    0.08
    ween
    0.08
     Firm
    0.08
    Activations Density 0.001%

    No Known Activations