© 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. 89049
    Prev
    Next
    INDEX
    Explanations

    Ash followed by ley or ville

    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
    akit
    -0.09
     Cain
    -0.09
    /Search
    -0.08
    à¸ģร
    -0.08
    icut
    -0.08
     bath
    -0.08
     Griffin
    -0.08
    770
    -0.08
    thouse
    -0.08
     OMX
    -0.08
    POSITIVE LOGITS
     Harley
    0.10
    lei
    0.10
     detected
    0.10
     pun
    0.10
    cr
    0.09
     Bian
    0.09
    riel
    0.09
     Bi
    0.09
     Honor
    0.09
     Bei
    0.09
    Activations Density 0.002%

    No Known Activations