© 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. 89385
    Prev
    Next
    INDEX
    Explanations

    ag + suffix

    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
    eer
    -0.11
     blazing
    -0.11
    cek
    -0.11
     Plenty
    -0.10
    ed
    -0.10
    KT
    -0.10
     Amazing
    -0.10
    eda
    -0.09
    402
    -0.09
     Legend
    -0.09
    POSITIVE LOGITS
    stick
    0.10
    etto
    0.09
     freely
    0.09
    identifier
    0.09
    hat
    0.09
     hateful
    0.09
    Sock
    0.09
    gy
    0.09
     gia
    0.09
    sticks
    0.09
    Activations Density 0.004%

    No Known Activations