© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 15790
    Prev
    Next
    INDEX
    Explanations

    approval and praise

    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
    atron
    -0.10
    ünd
    -0.09
    ds
    -0.09
     authorization
    -0.09
    avec
    -0.08
     somehow
    -0.08
     rebut
    -0.08
     absorbed
    -0.08
    usi
    -0.08
    otch
    -0.08
    POSITIVE LOGITS
     aloud
    0.14
     loudly
    0.14
     praised
    0.14
     applauded
    0.13
     hailed
    0.13
     efforts
    0.13
     praises
    0.12
     applaud
    0.12
     praise
    0.12
     publicly
    0.11
    Activations Density 0.064%

    No Known Activations