© 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. 3827
    Prev
    Next
    INDEX
    Explanations

    one of the

    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
     imperfect
    -0.09
    çŃ
    -0.08
    zy
    -0.08
     aver
    -0.08
    zo
    -0.08
    Concat
    -0.08
    olla
    -0.08
    Powered
    -0.08
    hold
    -0.07
     zo
    -0.07
    POSITIVE LOGITS
     standout
    0.22
     notable
    0.20
     noteworthy
    0.18
     key
    0.17
     prominent
    0.16
     unique
    0.15
     advantages
    0.15
     striking
    0.15
    unique
    0.14
     exciting
    0.14
    Activations Density 0.087%

    No Known Activations