© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27357
    Prev
    Next
    INDEX
    Explanations

    scoring methods

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases expressing importance or necessity using words like "important," "is," and "therefore."

    oai_token-act-pair · claude-4-5-haikuTriggered by @cam
    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
     romant
    -0.13
     unacceptable
    -0.12
     emotionally
    -0.11
    rzy
    -0.11
     romantic
    -0.11
     heterosexual
    -0.11
     physiological
    -0.10
     Cand
    -0.10
     Americas
    -0.10
     Honor
    -0.10
    POSITIVE LOGITS
    onus
    0.14
     bif
    0.11
     savvy
    0.10
     brows
    0.10
     cum
    0.10
     minut
    0.10
     concession
    0.09
     ponder
    0.09
     effortless
    0.08
    elig
    0.08
    Activations Density 0.329%

    No Known Activations