© 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. 90456
    Prev
    Next
    INDEX
    Explanations

    why use or wait

    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
    edo
    -0.12
     WTF
    -0.11
     Gad
    -0.10
    lov
    -0.09
     Amph
    -0.09
    adge
    -0.09
    478
    -0.09
    quoise
    -0.09
    337
    -0.09
    anton
    -0.09
    POSITIVE LOGITS
     unnecessarily
    0.13
    _when
    0.12
     bother
    0.11
     when
    0.11
     waste
    0.11
    when
    0.11
    When
    0.11
     bothers
    0.11
     troublesome
    0.10
     yourself
    0.10
    Activations Density 0.032%

    No Known Activations