© 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. 90240
    Prev
    Next
    INDEX
    Explanations

    under the

    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
    sch
    -0.12
    itz
    -0.11
    279
    -0.10
     meltdown
    -0.10
     thereof
    -0.10
    _RO
    -0.10
    idel
    -0.10
    .cx
    -0.10
     lanz
    -0.10
     Ramirez
    -0.10
    POSITIVE LOGITS
    ngine
    0.09
    RD
    0.09
    chy
    0.08
     entirety
    0.08
    amas
    0.08
     together
    0.08
    pend
    0.08
    ernes
    0.08
    ches
    0.08
    510
    0.08
    Activations Density 0.183%

    No Known Activations