© 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. 7446
    Prev
    Next
    INDEX
    Explanations

    Beer Hall Putsch

    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
     dude
    -0.12
     DERP
    -0.11
     slang
    -0.11
     Fucking
    -0.10
     Dude
    -0.10
     fuck
    -0.10
     fucking
    -0.09
     joke
    -0.09
     retarded
    -0.09
     dudes
    -0.09
    POSITIVE LOGITS
     GDPR
    0.13
    —I
    0.11
    âĢij
    0.11
     shutter
    0.11
    ––
    0.11
    -builder
    0.10
     Bes
    0.10
     Brexit
    0.10
     bespoke
    0.10
     Alg
    0.10
    Activations Density 0.091%

    No Known Activations