© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49224
    Prev
    Next
    INDEX
    Explanations

    this followed by a noun phrase

    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
    dat
    -0.09
     term
    -0.08
    ohl
    -0.08
     famous
    -0.08
    avin
    -0.08
     datum
    -0.08
     sturdy
    -0.08
    zin
    -0.07
     Vad
    -0.07
     Term
    -0.07
    POSITIVE LOGITS
    -this
    0.13
     whole
    0.13
    ãĥĶ
    0.12
     @$
    0.12
    whole
    0.12
     ordeal
    0.12
     newfound
    0.11
     McM
    0.11
     rut
    0.11
    &page
    0.11
    Activations Density 0.058%

    No Known Activations