© 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. 115225
    Prev
    Next
    INDEX
    Explanations

    offensive or harmful

    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
     apparently
    -0.13
     "".
    -0.10
     presumably
    -0.09
    –and
    -0.09
     ostensibly
    -0.09
    cw
    -0.09
    agra
    -0.09
     collo
    -0.09
     supposedly
    -0.09
     firstly
    -0.09
    POSITIVE LOGITS
    /my
    0.15
    /I
    0.13
     myself
    0.13
     my
    0.11
    !/
    0.11
     actively
    0.10
    /use
    0.10
    æĪijçļĦ
    0.10
     Buzz
    0.10
     ______
    0.10
    Activations Density 0.078%

    No Known Activations