© 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. 48188
    Prev
    Next
    INDEX
    Explanations

    granted, thankfully, obviously

    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
     my
    -0.12
     I
    -0.11
    (my
    -0.11
    .My
    -0.11
     thru
    -0.10
    (I
    -0.10
    .I
    -0.10
     recip
    -0.10
     (=
    -0.10
    Oops
    -0.10
    POSITIVE LOGITS
    Granted
    0.13
     Thankfully
    0.13
     Granted
    0.12
     Of
    0.11
     RELATED
    0.11
    Of
    0.11
     thankfully
    0.10
    Obviously
    0.10
    [js
    0.10
     plenty
    0.10
    Activations Density 0.105%

    No Known Activations