© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90564
    Prev
    Next
    INDEX
    Explanations

    themselves, collectively, yourselves, identities

    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
     itself
    -0.13
     lone
    -0.11
     alone
    -0.11
     Alone
    -0.10
     solitary
    -0.10
     herself
    -0.10
     himself
    -0.10
     lonely
    -0.10
     fleets
    -0.10
     solo
    -0.10
    POSITIVE LOGITS
     themselves
    0.33
     collectively
    0.22
     yourselves
    0.20
    —they
    0.19
     respectively
    0.18
     identities
    0.16
     weren
    0.16
     selves
    0.15
     were
    0.15
     individually
    0.15
    Activations Density 0.364%

    No Known Activations