© 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. 111996
    Prev
    Next
    INDEX
    Explanations

    trigonometric or AT&T

    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
     Whilst
    -0.12
     whilst
    -0.11
     unsur
    -0.11
    Whilst
    -0.11
     aforementioned
    -0.10
    Despite
    -0.10
     thus
    -0.10
     Needless
    -0.10
    Indeed
    -0.10
     merely
    -0.10
    POSITIVE LOGITS
     kinda
    0.12
    ï¼Īç¬ij
    0.12
     folks
    0.11
     OMG
    0.11
     gotta
    0.10
     detectives
    0.10
     dudes
    0.10
    fab
    0.10
     swirl
    0.10
     OK
    0.10
    Activations Density 0.016%

    No Known Activations