© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50718
    Prev
    Next
    INDEX
    Explanations

    counterculture and 1960s music

    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
     dynamically
    -0.11
     noir
    -0.10
     noct
    -0.10
     Dynam
    -0.09
    nite
    -0.09
     witty
    -0.09
     nightclub
    -0.09
     superhero
    -0.09
     Westminster
    -0.08
     Zag
    -0.08
    POSITIVE LOGITS
     hipp
    0.29
     Hipp
    0.25
     commune
    0.15
     preach
    0.13
     spiritual
    0.13
     Kund
    0.13
     era
    0.12
    -era
    0.12
     protesting
    0.12
     unk
    0.12
    Activations Density 0.098%

    No Known Activations