© 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. 113971
    Prev
    Next
    INDEX
    Explanations

    OF LICENSE

    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
     Baz
    -0.08
    inite
    -0.08
     caution
    -0.08
    aw
    -0.08
     mich
    -0.07
     note
    -0.07
     Platz
    -0.07
     sizing
    -0.07
    remark
    -0.07
     bump
    -0.07
    POSITIVE LOGITS
     contempl
    0.11
    Errors
    0.11
    ahr
    0.11
     ANY
    0.11
     arrang
    0.11
    mtree
    0.10
    pread
    0.10
     overrun
    0.10
    uros
    0.10
    esen
    0.10
    Activations Density 0.084%

    No Known Activations