© 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. 17641
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Weinstein
    -0.07
    elite
    -0.07
    aci
    -0.07
     hydr
    -0.07
    atem
    -0.07
    alls
    -0.07
    fur
    -0.07
     Dal
    -0.07
    æk
    -0.07
     fur
    -0.06
    POSITIVE LOGITS
    azu
    0.12
    Ñģп
    0.11
    inka
    0.11
     controlling
    0.10
    azar
    0.10
     PIX
    0.10
     ideally
    0.10
     hipp
    0.10
     ed
    0.10
    csr
    0.10
    Activations Density 0.000%

    No Known Activations