© 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. 4093
    Prev
    Next
    INDEX
    Explanations

    won't / won

    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
    rios
    -0.10
    bomb
    -0.09
    ented
    -0.09
    ITY
    -0.09
     multim
    -0.09
    ity
    -0.08
    cope
    -0.08
    bell
    -0.08
    aler
    -0.08
    ATER
    -0.08
    POSITIVE LOGITS
    ’t
    0.18
    't
    0.17
    kish
    0.14
    DER
    0.13
    fully
    0.12
    ’T
    0.12
    kie
    0.12
    ´t
    0.11
    nen
    0.11
    `t
    0.10
    Activations Density 0.018%

    No Known Activations