© 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. 114594
    Prev
    Next
    INDEX
    Explanations

    jacket

    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
    fulness
    -0.12
    fully
    -0.11
    ings
    -0.11
    lessly
    -0.10
    stuff
    -0.09
    nie
    -0.09
    heets
    -0.09
    noch
    -0.09
    bject
    -0.09
     Unblock
    -0.09
    POSITIVE LOGITS
    ed
    0.17
    ectomy
    0.13
    alian
    0.11
    ëĭ¹
    0.11
    ted
    0.10
    /co
    0.10
    ized
    0.10
    ing
    0.09
    nowled
    0.09
    /front
    0.09
    Activations Density 0.007%

    No Known Activations