© 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. 114254
    Prev
    Next
    INDEX
    Explanations

    sweet

    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
    aar
    -0.09
    aat
    -0.09
    adt
    -0.09
    dag
    -0.08
     Aeros
    -0.08
     TEN
    -0.08
     ditch
    -0.08
    ucus
    -0.08
    ummer
    -0.08
    edi
    -0.08
    POSITIVE LOGITS
    iez
    0.18
    ie
    0.17
    eners
    0.16
    ener
    0.16
    ening
    0.16
    -faced
    0.16
    ened
    0.16
    ness
    0.14
    heart
    0.14
    -looking
    0.13
    Activations Density 0.005%

    No Known Activations