© 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. 25398
    Prev
    Next
    INDEX
    Explanations

    active mechanisms, hiring, hostile, management, studied, control, flight, matrix

    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
     unle
    -0.09
     heavy
    -0.09
     surrogate
    -0.08
    ards
    -0.08
     Prev
    -0.08
    achi
    -0.08
     handc
    -0.08
    Heavy
    -0.08
     Palmer
    -0.08
     Lord
    -0.08
    POSITIVE LOGITS
    /pass
    0.25
     actively
    0.17
    -active
    0.17
     participation
    0.15
     participated
    0.14
     ingredient
    0.14
    (active
    0.14
     engaged
    0.14
    actively
    0.14
     dislike
    0.13
    Activations Density 0.103%

    No Known Activations