© 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. 17789
    Prev
    Next
    INDEX
    Explanations

    roman numerals after numbers

    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
    -0.13
     Shemale
    -0.11
     Farage
    -0.10
     www
    -0.10
     fulfil
    -0.10
    ,www
    -0.10
    DOWNLOAD
    -0.10
     Downloads
    -0.10
     :-↵
    -0.10
    -0.10
    POSITIVE LOGITS
     daÃŁ
    0.11
     rehearsal
    0.11
     Scene
    0.10
     RECORD
    0.10
     OMIT
    0.10
    annot
    0.10
    Scene
    0.10
     annotate
    0.10
    Narr
    0.10
     Transcript
    0.10
    Activations Density 0.177%

    No Known Activations