© 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. 6343
    Prev
    Next
    INDEX
    Explanations

    that followed by "this" or "a"

    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
     unfavor
    -0.07
    ture
    -0.07
     makes
    -0.07
     is
    -0.07
    atre
    -0.07
     Bark
    -0.07
     Bak
    -0.07
    odor
    -0.07
    -members
    -0.06
    ILA
    -0.06
    POSITIVE LOGITS
    ole
    0.14
     combination
    0.13
     proverb
    0.12
     infamous
    0.11
     underlying
    0.11
     mixture
    0.11
     dreaded
    0.11
     dabei
    0.11
    eres
    0.11
    emark
    0.11
    Activations Density 0.036%

    No Known Activations