© 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. 6180
    Prev
    Next
    INDEX
    Explanations

    author names

    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
    ilio
    -0.09
    jiang
    -0.09
    oton
    -0.09
    cio
    -0.09
    chos
    -0.09
     Sext
    -0.09
     Pemb
    -0.09
    ¾
    -0.08
     sext
    -0.08
     Pend
    -0.08
    POSITIVE LOGITS
     Katz
    0.11
    aval
    0.09
    aldi
    0.09
     nord
    0.09
    ihn
    0.09
    pee
    0.08
    -Speed
    0.08
     Weiner
    0.08
    Comp
    0.08
     Frost
    0.08
    Activations Density 0.001%

    No Known Activations