© 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. 14367
    Prev
    Next
    INDEX
    Explanations

    reciprocals and similar relationships

    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
    embr
    -0.12
    awe
    -0.12
     twilight
    -0.11
    eya
    -0.10
     estr
    -0.10
    eye
    -0.10
     bitterness
    -0.10
     Hort
    -0.10
     Salv
    -0.09
     Plymouth
    -0.09
    POSITIVE LOGITS
     likewise
    0.26
     similarly
    0.25
     equally
    0.21
     ALSO
    0.19
     also
    0.16
     Similarly
    0.16
     recip
    0.15
     ebenfalls
    0.15
    Similarly
    0.14
     suffered
    0.13
    Activations Density 0.072%

    No Known Activations