© 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. 32258
    Prev
    Next
    INDEX
    Explanations

    be sure to

    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
     repeatedly
    -0.14
     beforehand
    -0.13
     momentarily
    -0.12
     temporarily
    -0.12
     periodically
    -0.11
     wherever
    -0.11
     Lastly
    -0.10
    Lastly
    -0.10
     consistently
    -0.10
    perf
    -0.10
    POSITIVE LOGITS
     EVER
    0.16
     ausp
    0.12
     ever
    0.12
    ever
    0.11
     coinc
    0.11
    -ever
    0.11
     coincide
    0.11
    ahr
    0.09
     destined
    0.09
     Ever
    0.09
    Activations Density 0.322%

    No Known Activations