© 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. 92243
    Prev
    Next
    INDEX
    Explanations

    proximity and ease of access

    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
    dyn
    -0.10
     Critical
    -0.10
    Critical
    -0.10
     scrut
    -0.10
    undra
    -0.10
    дал
    -0.09
     critical
    -0.09
     nobody
    -0.09
    ownt
    -0.09
    annel
    -0.09
    POSITIVE LOGITS
     accessibility
    0.24
     easily
    0.21
     easiest
    0.20
     Accessibility
    0.20
     parking
    0.20
     reachable
    0.20
     easy
    0.19
     accessible
    0.19
     nearest
    0.18
    Accessibility
    0.18
    Activations Density 0.427%

    No Known Activations