© 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. 115910
    Prev
    Next
    INDEX
    Explanations

    qualities, abilities, or states

    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
     Norte
    -0.12
     vice
    -0.12
    Bookmark
    -0.11
    andest
    -0.11
     Faith
    -0.11
    /trunk
    -0.11
     inaug
    -0.11
     smack
    -0.11
     vag
    -0.11
     им
    -0.11
    POSITIVE LOGITS
     ability
    0.13
     undeniable
    0.10
     qualities
    0.09
     abilities
    0.09
     alone
    0.08
     charm
    0.08
    923
    0.08
     versatility
    0.08
     unmatched
    0.08
    994
    0.08
    Activations Density 0.092%

    No Known Activations