© 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. 114565
    Prev
    Next
    INDEX
    Explanations

    forced confessions, extracting, coaxing

    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
    ycz
    -0.10
     Aub
    -0.10
     assort
    -0.10
     tackled
    -0.09
    aran
    -0.09
    vor
    -0.09
    athy
    -0.09
    hev
    -0.09
     assaults
    -0.09
    tf
    -0.09
    POSITIVE LOGITS
     confession
    0.20
     elic
    0.17
     extracting
    0.16
     coax
    0.16
     extraction
    0.16
     confessed
    0.15
     extract
    0.15
     extracted
    0.15
     Extract
    0.15
    extract
    0.14
    Activations Density 0.058%

    No Known Activations