© 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. 90514
    Prev
    Next
    INDEX
    Explanations

    worldly cosmopolitan, cultured, secular

    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
    vik
    -0.11
     Uph
    -0.10
     Highway
    -0.09
     Bee
    -0.09
     Traditional
    -0.09
     Hod
    -0.09
    IELDS
    -0.09
    ück
    -0.09
     Stick
    -0.09
    hev
    -0.09
    POSITIVE LOGITS
     worldly
    0.19
     sophistic
    0.18
     sophistication
    0.17
     cosm
    0.16
     sophisticated
    0.15
     refined
    0.14
     cultured
    0.13
    opolitan
    0.13
     urban
    0.13
     refine
    0.13
    Activations Density 0.046%

    No Known Activations