© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    decision or dilemma

    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
     dir
    -0.11
    iskey
    -0.11
     mans
    -0.11
     prep
    -0.10
     obey
    -0.10
    ilan
    -0.10
     obe
    -0.10
     kickoff
    -0.10
    omanip
    -0.10
     adap
    -0.10
    POSITIVE LOGITS
     weighing
    0.19
     deliber
    0.18
     Decision
    0.17
     decision
    0.17
     inde
    0.16
    Decision
    0.16
    weigh
    0.16
     weigh
    0.15
     undecided
    0.15
     weighs
    0.14
    Activations Density 0.102%

    No Known Activations