© 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. 112563
    Prev
    Next
    INDEX
    Explanations

    heart and soul

    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
     contracted
    -0.10
     incumb
    -0.09
    illac
    -0.09
     exert
    -0.09
    inus
    -0.09
     muscular
    -0.08
     oblivious
    -0.08
     breathing
    -0.08
     teg
    -0.08
     prostit
    -0.08
    POSITIVE LOGITS
     soul
    0.16
     inside
    0.16
     heart
    0.15
     fundamentally
    0.15
     trapped
    0.15
     spirit
    0.14
    heart
    0.14
     underneath
    0.14
     coraz
    0.14
     hearts
    0.14
    Activations Density 0.069%

    No Known Activations