© 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. 113086
    Prev
    Next
    INDEX
    Explanations

    aside

    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
    ombre
    -0.09
    abble
    -0.09
    elong
    -0.09
    anken
    -0.09
     cbo
    -0.09
    ÃŃv
    -0.09
     Mask
    -0.09
    ONO
    -0.08
    ãģ¡ãģ¯
    -0.08
     Bas
    -0.08
    POSITIVE LOGITS
     notwithstanding
    0.22
     included
    0.18
     intact
    0.16
    included
    0.13
     INCLUDED
    0.12
    withstanding
    0.11
     aside
    0.11
     inclusive
    0.11
     inclus
    0.10
    ardless
    0.10
    Activations Density 0.044%

    No Known Activations