© 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. 89980
    Prev
    Next
    INDEX
    Explanations

    PH, CH, HH abbreviations

    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
     Zi
    -0.09
     Newman
    -0.09
     Malone
    -0.09
    zem
    -0.08
     Leone
    -0.08
     Monter
    -0.08
     Locker
    -0.08
     appendString
    -0.08
    oldt
    -0.08
    fuse
    -0.08
    POSITIVE LOGITS
     LH
    0.40
     EH
    0.39
     BH
    0.38
     MH
    0.37
     FH
    0.37
     VH
    0.36
     RH
    0.36
     IH
    0.36
     DH
    0.35
    RH
    0.35
    Activations Density 1.158%

    No Known Activations