© 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. 7494
    Prev
    Next
    INDEX
    Explanations

    pronouns following special character

    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
     zug
    -0.10
    cj
    -0.10
     Cob
    -0.09
     Tos
    -0.09
     Leban
    -0.09
    ablish
    -0.09
     Eins
    -0.09
     cob
    -0.09
    wer
    -0.09
     Im
    -0.08
    POSITIVE LOGITS
     them
    0.20
     him
    0.14
    them
    0.14
     their
    0.12
    'em
    0.11
     your
    0.10
     us
    0.10
     enough
    0.10
     thereof
    0.10
    him
    0.09
    Activations Density 0.167%

    No Known Activations