© 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. 90268
    Prev
    Next
    INDEX
    Explanations

    don't want 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
    alta
    -0.12
     briefly
    -0.10
    adt
    -0.10
     clap
    -0.10
     nad
    -0.10
    sut
    -0.10
     borders
    -0.10
    oom
    -0.09
    bsolute
    -0.09
    igt
    -0.09
    POSITIVE LOGITS
     nor
    0.25
     unnecessarily
    0.22
     anymore
    0.18
     prematurely
    0.17
     Nor
    0.15
    nor
    0.15
    Nor
    0.14
     inadvertently
    0.12
     unnecessary
    0.11
     especially
    0.11
    Activations Density 0.071%

    No Known Activations