© 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. 88189
    Prev
    Next
    INDEX
    Explanations

    references oneself or others

    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
     Mata
    -0.10
     denomination
    -0.10
    iban
    -0.09
    ÑĩеÑĤ
    -0.09
    enia
    -0.09
     ath
    -0.09
    zá
    -0.09
    adr
    -0.09
     sof
    -0.09
    du
    -0.08
    POSITIVE LOGITS
     selves
    0.25
     me
    0.22
     herself
    0.20
     him
    0.20
     yourself
    0.20
     ourselves
    0.20
     YOU
    0.19
    him
    0.19
     himself
    0.18
     myself
    0.18
    Activations Density 0.173%

    No Known Activations