© 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. 50079
    Prev
    Next
    INDEX
    Explanations

    gag, af, ago, tagged, GHC

    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
     templ
    -0.09
     scour
    -0.09
     rocking
    -0.09
    rock
    -0.09
     regards
    -0.09
     clas
    -0.09
    quin
    -0.08
    templ
    -0.08
     corr
    -0.08
     Ere
    -0.08
    POSITIVE LOGITS
     gag
    0.15
     reflex
    0.14
    ingly
    0.13
     Princip
    0.12
    ging
    0.12
     Reflex
    0.12
    gle
    0.11
     choked
    0.11
    ged
    0.11
     fetish
    0.10
    Activations Density 0.001%

    No Known Activations