© 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. 90035
    Prev
    Next
    INDEX
    Explanations

    buy one, give one

    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
    NESS
    -0.13
     WON
    -0.13
    /cop
    -0.11
    ness
    -0.11
    rière
    -0.11
    .Must
    -0.11
    ries
    -0.10
    rier
    -0.10
    hots
    -0.10
    imers
    -0.10
    POSITIVE LOGITS
     yourself
    0.27
     Yourself
    0.27
     yourselves
    0.25
    -your
    0.23
     your
    0.21
     Your
    0.19
    your
    0.18
     me
    0.17
     Me
    0.17
    -the
    0.16
    Activations Density 0.492%

    No Known Activations