© 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. 47085
    Prev
    Next
    INDEX
    Explanations

    includes, file tags, or code headers

    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
     Sass
    -0.09
     Almighty
    -0.08
    OMB
    -0.08
    -To
    -0.08
     cerv
    -0.07
     vit
    -0.07
     filetype
    -0.07
     ép
    -0.07
     Btn
    -0.07
     cata
    -0.07
    POSITIVE LOGITS
    adin
    0.10
     Hao
    0.10
    bling
    0.10
    ><![
    0.09
     Ori
    0.09
    Insert
    0.09
     outr
    0.09
    .inline
    0.09
     sic
    0.09
    esper
    0.09
    Activations Density 0.173%

    No Known Activations