© 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. 89613
    Prev
    Next
    INDEX
    Explanations

    greetings and thanks

    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
    esion
    -0.09
    —to
    -0.09
     (*)
    -0.09
    lim
    -0.08
     pen
    -0.08
    zel
    -0.08
    ANA
    -0.08
    atori
    -0.08
     iam
    -0.08
     Gallagher
    -0.08
    POSITIVE LOGITS
     Mits
    0.10
    ({},
    0.10
    Hi
    0.10
     Hi
    0.10
     :,
    0.10
    {},
    0.09
    orry
    0.09
    allo
    0.09
    ',$
    0.09
    (_,
    0.09
    Activations Density 0.177%

    No Known Activations