© 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. 114089
    Prev
    Next
    INDEX
    Explanations

    contextual number division

    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
     fucked
    -0.14
     fucking
    -0.12
     shit
    -0.12
     fucks
    -0.11
    ?↵↵↵↵
    -0.11
    —all
    -0.11
     fuck
    -0.11
     Fucking
    -0.11
    âĢ¦↵↵↵↵
    -0.10
    ’s
    -0.10
    POSITIVE LOGITS
     alot
    0.11
    ANS
    0.10
    Wiki
    0.10
     seper
    0.10
     Whilst
    0.10
     recieved
    0.10
     whilst
    0.09
     tha
    0.09
     '
    0.09
     "
    0.09
    Activations Density 0.232%

    No Known Activations