© 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. 16467
    Prev
    Next
    INDEX
    Explanations

    negative contractions

    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
     (!!
    -0.11
     unlocks
    -0.10
    tracer
    -0.09
     mmc
    -0.09
    371
    -0.09
    avail
    -0.09
     mim
    -0.09
     fille
    -0.09
    efe
    -0.09
     Originally
    -0.09
    POSITIVE LOGITS
     isn
    0.21
     rarely
    0.19
     aren
    0.19
     doesn
    0.18
     hardly
    0.18
     only
    0.18
     seldom
    0.17
     hasn
    0.17
     barely
    0.17
     wouldn
    0.16
    Activations Density 0.251%

    No Known Activations