© 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. 114313
    Prev
    Next
    INDEX
    Explanations

    Are you/there/is this/could this be

    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
    iaux
    -0.12
     supposedly
    -0.11
     ple
    -0.11
     probably
    -0.11
     Jag
    -0.10
     Rag
    -0.10
     youre
    -0.10
     presumably
    -0.10
     plenty
    -0.10
     pretty
    -0.10
    POSITIVE LOGITS
    ?
    0.12
    ?!
    0.10
     really
    0.10
    ?,
    0.09
    ???
    0.09
    !?
    0.09
     Really
    0.09
     Rodney
    0.08
     myself
    0.08
     possible
    0.08
    Activations Density 0.028%

    No Known Activations