© 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. 50218
    Prev
    Next
    INDEX
    Explanations

    placed on / mounted on / against

    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
     inside
    -0.12
     gaz
    -0.10
     underneath
    -0.10
     inserting
    -0.10
     insert
    -0.09
     inserted
    -0.09
     purs
    -0.09
     under
    -0.09
     adm
    -0.09
    UNDER
    -0.09
    POSITIVE LOGITS
     atop
    0.14
     over
    0.11
     onto
    0.10
     Hir
    0.10
    atham
    0.10
     bord
    0.10
    birthday
    0.09
     sobre
    0.09
    ois
    0.09
    Over
    0.09
    Activations Density 0.049%

    No Known Activations