© 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. 46853
    Prev
    Next
    INDEX
    Explanations

    in, for, on, from, Monday, uploaded

    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
     yourself
    -0.18
    your
    -0.16
     your
    -0.15
    you
    -0.14
     YOUR
    -0.13
     you
    -0.13
    ä½ł
    -0.13
     yourselves
    -0.11
     ваÑĪ
    -0.11
     youre
    -0.11
    POSITIVE LOGITS
     my
    0.21
     test
    0.21
     myself
    0.21
     testing
    0.20
     testers
    0.20
    æµĭè¯ķ
    0.20
    æĪijçļĦ
    0.20
     tested
    0.20
     experiment
    0.18
     hubby
    0.17
    Activations Density 0.398%

    No Known Activations