© 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. 114276
    Prev
    Next
    INDEX
    Explanations

    "how i roll"

    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
     idiot
    -0.11
     nause
    -0.09
     grat
    -0.09
     pkg
    -0.09
     Interesting
    -0.09
     Funny
    -0.08
     humour
    -0.08
     Lovely
    -0.08
     dreadful
    -0.08
     Idea
    -0.08
    POSITIVE LOGITS
     ain
    0.23
     gotta
    0.20
     Ain
    0.18
     yo
    0.18
     gonna
    0.18
     booty
    0.18
     dudes
    0.16
     badass
    0.16
     hustle
    0.16
     dat
    0.15
    Activations Density 0.206%

    No Known Activations