© 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. 114228
    Prev
    Next
    INDEX
    Explanations

    wondering, curious, found, excited

    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
    ahn
    -0.09
    ibel
    -0.09
    /=
    -0.09
     sudden
    -0.08
     Honest
    -0.08
    hq
    -0.08
    ahu
    -0.08
    ject
    -0.08
     Lah
    -0.08
    å¤Ħ
    -0.08
    POSITIVE LOGITS
     thrilled
    0.17
     glad
    0.17
     thrill
    0.17
     dismay
    0.17
     delight
    0.17
     marvel
    0.16
     amazed
    0.16
     grat
    0.16
     delighted
    0.16
     pleased
    0.15
    Activations Density 0.283%

    No Known Activations