© 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. 89550
    Prev
    Next
    INDEX
    Explanations

    or something

    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
     somehow
    -0.15
    adro
    -0.12
    ivan
    -0.12
     vez
    -0.11
     Somehow
    -0.11
     perhaps
    -0.11
    perhaps
    -0.11
    abad
    -0.10
    iliar
    -0.10
    /general
    -0.10
    POSITIVE LOGITS
     stuff
    0.16
     such
    0.14
     something
    0.14
     anything
    0.11
     everything
    0.11
    thing
    0.11
     things
    0.10
    something
    0.10
    such
    0.10
    stuff
    0.09
    Activations Density 0.031%

    No Known Activations