© 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. 92142
    Prev
    Next
    INDEX
    Explanations

    secret Base

    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
     whore
    -0.10
     bitch
    -0.10
     raped
    -0.10
     tranny
    -0.09
     fucks
    -0.09
     rapes
    -0.09
     rape
    -0.09
     hurting
    -0.09
     fucked
    -0.09
     franch
    -0.09
    POSITIVE LOGITS
     handshake
    0.15
     secret
    0.14
     RSVP
    0.13
     VIP
    0.13
     nos
    0.13
     backstage
    0.12
     teleport
    0.12
     disco
    0.12
     gossip
    0.12
     superhero
    0.12
    Activations Density 0.039%

    No Known Activations