© 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. 49836
    Prev
    Next
    INDEX
    Explanations

    positive sentiment following certain words

    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
     NY
    -0.16
    NY
    -0.15
     learnt
    -0.15
     onwards
    -0.14
     expiry
    -0.13
     honoured
    -0.13
     happily
    -0.13
     NYC
    -0.13
     provinc
    -0.13
     Bronx
    -0.12
    POSITIVE LOGITS
     dang
    0.16
     preacher
    0.13
     evidently
    0.13
     dern
    0.11
     UIL
    0.11
     furnished
    0.11
     Ole
    0.11
     Quit
    0.10
     quit
    0.10
     Erl
    0.10
    Activations Density 0.758%

    No Known Activations