© 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. 16001
    Prev
    Next
    INDEX
    Explanations

    not enough or sufficient

    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
    acz
    -0.09
     hesitant
    -0.08
     Tin
    -0.08
     continu
    -0.07
     Cabin
    -0.07
     Jelly
    -0.07
     Den
    -0.07
     rever
    -0.07
     inhabit
    -0.07
     habe
    -0.07
    POSITIVE LOGITS
     insufficient
    0.20
     enough
    0.18
     sufficient
    0.17
     suffice
    0.17
     Enough
    0.16
     suff
    0.15
    Enough
    0.15
     satisfaction
    0.15
     satisfied
    0.14
     wasn
    0.14
    Activations Density 0.108%

    No Known Activations