© 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. 114278
    Prev
    Next
    INDEX
    Explanations

    Sha-, Sa-, Sans-, Sam-, Sah-

    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
    lug
    -0.11
     mult
    -0.11
    weep
    -0.09
    Ø°
    -0.09
     incremental
    -0.08
     sle
    -0.08
    mult
    -0.08
    ORIA
    -0.08
     distra
    -0.08
    ding
    -0.08
    POSITIVE LOGITS
    \e
    0.09
     wil
    0.09
    clar
    0.09
     permanently
    0.09
    emm
    0.09
    atus
    0.09
    Wil
    0.09
     unconditional
    0.08
    ahl
    0.08
     deserted
    0.08
    Activations Density 0.015%

    No Known Activations