© 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. 91321
    Prev
    Next
    INDEX
    Explanations

    like

    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
    adin
    -0.08
     somehow
    -0.08
    itar
    -0.08
    enge
    -0.08
     âĢº
    -0.08
    ]?
    -0.08
     Arbit
    -0.08
    asar
    -0.08
    ri
    -0.08
    halt
    -0.08
    POSITIVE LOGITS
     like
    0.40
     Like
    0.33
    Like
    0.30
    åĥı
    0.30
    like
    0.30
     LIKE
    0.25
     me
    0.22
     comme
    0.22
    _like
    0.22
     zoals
    0.21
    Activations Density 0.251%

    No Known Activations