© 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. 88650
    Prev
    Next
    INDEX
    Explanations

    reporting speech or statements

    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
     hin
    -0.11
    zin
    -0.10
    hed
    -0.09
     tremend
    -0.09
     ance
    -0.09
     independ
    -0.09
     Alumni
    -0.09
     VIP
    -0.09
     Buildings
    -0.09
     Tmin
    -0.09
    POSITIVE LOGITS
     spokeswoman
    0.14
     spokesman
    0.12
     Dr
    0.11
     spokesperson
    0.10
     said
    0.10
    obl
    0.10
     unnamed
    0.10
     preferences
    0.09
    said
    0.09
     outgoing
    0.09
    Activations Density 0.006%

    No Known Activations