© 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. 16846
    Prev
    Next
    INDEX
    Explanations

    speaker relative pronouns

    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
    furt
    -0.10
     Bere
    -0.09
    elsen
    -0.09
     Nun
    -0.09
    aus
    -0.09
    WX
    -0.09
     sibling
    -0.09
    _GP
    -0.09
    hints
    -0.09
     cardinal
    -0.09
    POSITIVE LOGITS
     whose
    0.20
    whose
    0.18
     who
    0.17
    who
    0.16
     whom
    0.12
     quien
    0.12
    lix
    0.10
     коÑĤоÑĢÑĭй
    0.09
     speaking
    0.09
     Catal
    0.09
    Activations Density 0.017%

    No Known Activations