© 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. 4538
    Prev
    Next
    INDEX
    Explanations

    helping or helped

    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
     Help
    -0.14
     help
    -0.13
    help
    -0.12
    _help
    -0.11
    HELP
    -0.11
    -help
    -0.10
     helps
    -0.10
    _helper
    -0.10
    Help
    -0.10
     HELP
    -0.09
    POSITIVE LOGITS
    lessly
    0.23
    desk
    0.19
    lessness
    0.19
    fully
    0.17
    mate
    0.14
    meet
    0.13
    Mate
    0.12
    mates
    0.11
    ful
    0.11
     drive
    0.11
    Activations Density 0.078%

    No Known Activations