© 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. 90478
    Prev
    Next
    INDEX
    Explanations

    fucking shit

    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
     Huff
    -0.12
    ecal
    -0.10
     flank
    -0.10
     Rover
    -0.08
    rend
    -0.08
     trunk
    -0.08
     Heck
    -0.08
     Trek
    -0.08
    KM
    -0.08
     trou
    -0.08
    POSITIVE LOGITS
     intents
    0.09
    LLU
    0.09
    minster
    0.09
    drivers
    0.09
    essor
    0.08
     grav
    0.08
     placeholder
    0.08
     FAC
    0.08
     marry
    0.08
     thirsty
    0.08
    Activations Density 0.012%

    No Known Activations