© 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. 49700
    Prev
    Next
    INDEX
    Explanations

    raise children, growth, inheritance

    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
     orgas
    -0.12
     reluct
    -0.12
    Transformation
    -0.12
     Transformation
    -0.12
     transformation
    -0.12
     Pregn
    -0.12
     Pregnancy
    -0.12
     pregnancy
    -0.12
    zik
    -0.11
    imports
    -0.11
    POSITIVE LOGITS
     inherit
    0.16
     raised
    0.14
     inher
    0.13
     grow
    0.13
     inherits
    0.13
     Raised
    0.11
     upbringing
    0.11
     grows
    0.11
     destined
    0.11
    raised
    0.11
    Activations Density 0.612%

    No Known Activations