© 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. 32275
    Prev
    Next
    INDEX
    Explanations

    devices, tools, attachments, procedures

    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
     comfy
    -0.18
     tricky
    -0.15
     pronto
    -0.15
     tweaks
    -0.14
     bigger
    -0.14
     mighty
    -0.13
     pals
    -0.13
     rej
    -0.13
     goodies
    -0.13
     lots
    -0.13
    POSITIVE LOGITS
     utilizing
    0.18
     utilizes
    0.17
     utilize
    0.16
     principally
    0.15
     resultant
    0.15
     utilized
    0.15
     persons
    0.14
     primarily
    0.14
    util
    0.13
     prior
    0.13
    Activations Density 8.521%

    No Known Activations