© 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. 49425
    Prev
    Next
    INDEX
    Explanations

    reluctant to

    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
     bamb
    -0.07
     brisk
    -0.07
    bomb
    -0.07
     Koh
    -0.07
    irt
    -0.07
    olor
    -0.07
    Bomb
    -0.06
    elts
    -0.06
    ine
    -0.06
     Nie
    -0.06
    POSITIVE LOGITS
    /inc
    0.16
     reluctant
    0.16
     reluct
    0.15
    /un
    0.15
     unwilling
    0.13
     participant
    0.13
    /im
    0.13
    elige
    0.13
     hesitant
    0.13
     endings
    0.12
    Activations Density 0.008%

    No Known Activations