© 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. 31010
    Prev
    Next
    INDEX
    Explanations

    like, mimic, emulate, gotten

    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
    ÙĪد
    -0.11
    izi
    -0.11
     lagi
    -0.10
    rego
    -0.10
     again
    -0.10
     virgin
    -0.10
     differently
    -0.10
     Reverse
    -0.10
     antid
    -0.09
    zi
    -0.09
    POSITIVE LOGITS
     like
    0.22
     Like
    0.19
     emulate
    0.17
    åĥı
    0.17
    Like
    0.17
    _like
    0.16
     mimic
    0.16
     LIKE
    0.16
     adopted
    0.14
    like
    0.14
    Activations Density 0.226%

    No Known Activations