© 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. 7206
    Prev
    Next
    INDEX
    Explanations

    More Views, Content, Facts, Video

    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
     than
    -0.18
    than
    -0.16
    -than
    -0.15
    Than
    -0.12
     Than
    -0.10
     THAN
    -0.10
    _than
    -0.09
    vier
    -0.09
    TRL
    -0.09
     compared
    -0.08
    POSITIVE LOGITS
     Orr
    0.10
     Para
    0.10
     sufficiently
    0.10
    first
    0.09
     CB
    0.09
     first
    0.09
    bero
    0.09
     perfectly
    0.09
    aea
    0.09
     orient
    0.09
    Activations Density 0.176%

    No Known Activations