© 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. 114187
    Prev
    Next
    INDEX
    Explanations

    mentioning or preceding word

    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
     thereof
    -0.12
    uft
    -0.11
     â
    -0.10
    \brief
    -0.09
    ÃĤ
    -0.09
    arn
    -0.09
    AREN
    -0.09
    asma
    -0.09
    orgeous
    -0.09
    arter
    -0.09
    POSITIVE LOGITS
     aforementioned
    0.26
     afore
    0.17
     mentioned
    0.13
    zag
    0.09
     Hale
    0.09
    <|fim_suffix|>
    0.09
     disg
    0.09
    mentioned
    0.08
     still
    0.08
     Wie
    0.08
    Activations Density 0.220%

    No Known Activations