© 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. 47597
    Prev
    Next
    INDEX
    Explanations

    slack and lax

    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
    ancial
    -0.08
    ige
    -0.08
    -pattern
    -0.08
     scars
    -0.08
    assi
    -0.08
    çķĮ
    -0.08
    /stat
    -0.08
    atte
    -0.08
    oppable
    -0.08
     Marathon
    -0.08
    POSITIVE LOGITS
    ening
    0.20
    ened
    0.19
     slack
    0.19
     jaw
    0.16
    jaw
    0.16
    slack
    0.15
    lining
    0.14
     jaws
    0.13
     Slack
    0.13
    ness
    0.12
    Activations Density 0.005%

    No Known Activations