© 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. 112141
    Prev
    Next
    INDEX
    Explanations

    Corning, Pacific Rim

    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
    qq
    -0.11
     millenn
    -0.10
    oba
    -0.10
     gris
    -0.10
    chten
    -0.10
    Sig
    -0.10
    odo
    -0.09
     egt
    -0.09
    temps
    -0.09
    etz
    -0.09
    POSITIVE LOGITS
    /me
    0.08
     Walker
    0.07
     grav
    0.07
     cart
    0.07
    -->
    0.07
     Radical
    0.07
     stagger
    0.06
    Walker
    0.06
     (__
    0.06
     Wol
    0.06
    Activations Density 0.020%

    No Known Activations