© 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. 114458
    Prev
    Next
    INDEX
    Explanations

    college, club, home, or protein activities

    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
     opportunity
    -0.11
     Voices
    -0.10
     voices
    -0.10
     situation
    -0.09
    voices
    -0.09
    playing
    -0.09
     ric
    -0.08
    Vo
    -0.08
    ordo
    -0.08
     contributions
    -0.08
    POSITIVE LOGITS
     amounts
    0.12
    uster
    0.11
    istically
    0.11
     laps
    0.10
    actively
    0.10
     Amount
    0.10
    urally
    0.10
    ially
    0.10
    fel
    0.09
    gren
    0.09
    Activations Density 0.807%

    No Known Activations