© 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. 88274
    Prev
    Next
    INDEX
    Explanations

    vaulted interiors

    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
     Slut
    -0.13
     crippled
    -0.12
     shitty
    -0.12
     incest
    -0.12
     prostitutes
    -0.12
     cuckold
    -0.11
     hentai
    -0.11
     masturb
    -0.11
     childish
    -0.11
     Fetish
    -0.11
    POSITIVE LOGITS
     handsome
    0.10
     seasoned
    0.09
     heavyweight
    0.09
     powerhouse
    0.08
     straightforward
    0.08
     interiors
    0.08
    Âł↵
    0.08
     solid
    0.08
     discern
    0.08
     hungry
    0.08
    Activations Density 0.023%

    No Known Activations