© 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. 49510
    Prev
    Next
    INDEX
    Explanations

    fall 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
    yne
    -0.09
    ike
    -0.08
    NT
    -0.07
    nown
    -0.07
    ovation
    -0.07
    cir
    -0.07
    abh
    -0.07
    riv
    -0.07
     refusing
    -0.07
    432
    -0.07
    POSITIVE LOGITS
     Laure
    0.11
     conclusions
    0.11
     extremes
    0.10
    asca
    0.10
    eps
    0.10
    ths
    0.10
     catch
    0.10
    mes
    0.10
    ingly
    0.10
    ","",
    0.10
    Activations Density 0.090%

    No Known Activations