© 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. 27495
    Prev
    Next
    INDEX
    Explanations

    instead or nor

    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
     without
    -0.12
    without
    -0.10
     vol
    -0.08
     Without
    -0.08
    ìķ¼
    -0.08
     WITHOUT
    -0.08
     Unfortunately
    -0.08
    isa
    -0.08
    Kent
    -0.08
     followed
    -0.08
    POSITIVE LOGITS
     nor
    0.23
     sondern
    0.23
     Instead
    0.22
    Instead
    0.22
     preferring
    0.19
    nor
    0.18
     merely
    0.17
     instead
    0.17
     just
    0.17
     except
    0.16
    Activations Density 0.304%

    No Known Activations