© 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. 30759
    Prev
    Next
    INDEX
    Explanations

    without sacrificing or compromising

    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
     Hus
    -0.09
    zin
    -0.08
     Ut
    -0.08
     unfortunately
    -0.08
    Bu
    -0.08
    ÑĮ
    -0.07
    ARN
    -0.07
    angan
    -0.07
    ivas
    -0.07
    aub
    -0.07
    POSITIVE LOGITS
     unaffected
    0.20
     integrity
    0.19
     intact
    0.19
     existing
    0.19
     unchanged
    0.19
     adversely
    0.18
     sacrificing
    0.17
     jeopard
    0.16
     Existing
    0.16
     negatively
    0.16
    Activations Density 0.461%

    No Known Activations