© 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. 115563
    Prev
    Next
    INDEX
    Explanations

    don't / do not commands

    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
    illo
    -0.09
     Fle
    -0.08
     barring
    -0.08
     either
    -0.08
     Jou
    -0.08
     disastrous
    -0.08
     sanity
    -0.08
    leo
    -0.08
     disastr
    -0.08
     dit
    -0.08
    POSITIVE LOGITS
     hesitate
    0.23
     rush
    0.18
     worry
    0.18
     hes
    0.17
     hesitation
    0.16
     worries
    0.14
     hurry
    0.14
     forget
    0.14
     underestimate
    0.13
    hes
    0.13
    Activations Density 0.015%

    No Known Activations