© 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. 116012
    Prev
    Next
    INDEX
    Explanations

    numbers and titles

    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
     Triple
    -0.10
    sla
    -0.09
     hete
    -0.09
     Freak
    -0.09
     polluted
    -0.09
    Triple
    -0.09
    Äĩ
    -0.09
    ase
    -0.08
     triple
    -0.08
    946
    -0.08
    POSITIVE LOGITS
    rok
    0.09
     PM
    0.09
    kos
    0.09
    nic
    0.09
     Zimmer
    0.09
    how
    0.09
     hol
    0.09
    four
    0.08
    éĹ®
    0.08
     larg
    0.08
    Activations Density 0.018%

    No Known Activations