© 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. 16673
    Prev
    Next
    INDEX
    Explanations

    starts new sentence

    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
    Lastly
    -0.14
     Lastly
    -0.13
     stew
    -0.11
     Finally
    -0.11
    rawn
    -0.10
    Finally
    -0.10
    inally
    -0.10
     Bugs
    -0.09
     finally
    -0.09
     ETA
    -0.09
    POSITIVE LOGITS
     Firstly
    0.10
    uce
    0.10
    ibel
    0.10
     Diamonds
    0.09
     bern
    0.09
    First
    0.09
    ,âĢ¦
    0.09
     First
    0.09
    é¦ĸ
    0.09
     inher
    0.09
    Activations Density 0.039%

    No Known Activations