© 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. 5720
    Prev
    Next
    INDEX
    Explanations

    list separators

    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
    —he
    -0.08
     he
    -0.07
    nam
    -0.07
     appalling
    -0.07
    ailer
    -0.07
     cheering
    -0.07
    583
    -0.07
     Couple
    -0.06
     namely
    -0.06
     they
    -0.06
    POSITIVE LOGITS
     realizing
    0.19
     sensing
    0.18
     meanwhile
    0.18
     having
    0.17
     unable
    0.16
     now
    0.15
     meantime
    0.15
     feeling
    0.14
     whose
    0.14
     despite
    0.14
    Activations Density 0.057%

    No Known Activations