© 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. 91860
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
     gated
    -0.10
     blocked
    -0.09
     skips
    -0.09
     Exercises
    -0.09
     hire
    -0.09
     Ultr
    -0.09
    áºŃt
    -0.09
     XCT
    -0.09
    atable
    -0.09
    recent
    -0.09
    POSITIVE LOGITS
    lus
    0.10
     stom
    0.10
    EMU
    0.10
     Tier
    0.09
     tit
    0.09
     Lange
    0.09
    ¶
    0.08
     Burton
    0.08
    æĺŁ
    0.08
     Anglic
    0.08
    Activations Density 0.071%

    No Known Activations