© 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. 4281
    Prev
    Next
    INDEX
    Explanations

    enough

    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
    abo
    -0.11
    ereo
    -0.10
    -AA
    -0.10
     Stevenson
    -0.10
    ura
    -0.10
    IGO
    -0.10
     Bir
    -0.10
    ansa
    -0.10
    CESS
    -0.09
    oday
    -0.09
    POSITIVE LOGITS
     enough
    0.86
     sufficiently
    0.69
     Enough
    0.68
    Enough
    0.55
     sufficient
    0.54
    ufficient
    0.31
     suf
    0.29
    è¶
    0.25
    -en
    0.24
     assez
    0.24
    Activations Density 0.865%

    No Known Activations