© 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. 27421
    Prev
    Next
    INDEX
    Explanations

    a list item marker

    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
     outlaw
    -0.09
     bust
    -0.08
    ussen
    -0.08
    hed
    -0.08
    ugen
    -0.07
    uchen
    -0.07
    leo
    -0.07
    bsp
    -0.07
    ayan
    -0.07
    nbsp
    -0.07
    POSITIVE LOGITS
    aaaa
    0.14
    And
    0.13
    aaa
    0.11
     Fischer
    0.11
    âĢ¦and
    0.11
     Roo
    0.11
    and
    0.11
     Redistributions
    0.11
    AND
    0.10
    aa
    0.10
    Activations Density 0.051%

    No Known Activations