© 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. 27819
    Prev
    Next
    INDEX
    Explanations

    as [adjective/adverb]

    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
     unb
    -0.08
     dire
    -0.08
     liken
    -0.08
     gig
    -0.08
     forb
    -0.08
    ascal
    -0.07
    ldr
    -0.07
     relate
    -0.07
     ra
    -0.07
    chor
    -0.07
    POSITIVE LOGITS
     consequence
    0.14
    ume
    0.12
     Ung
    0.11
    etto
    0.10
    well
    0.10
    cum
    0.10
    osi
    0.10
     soon
    0.10
    anium
    0.10
    eny
    0.10
    Activations Density 0.251%

    No Known Activations