© 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. 113631
    Prev
    Next
    INDEX
    Explanations

    of

    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
     precip
    -0.10
     '
    -0.08
     trailed
    -0.08
    ASI
    -0.08
     Aub
    -0.08
     budd
    -0.08
    ilon
    -0.08
    \č↵
    -0.08
    886
    -0.08
    elper
    -0.08
    POSITIVE LOGITS
    reuse
    0.09
    adt
    0.09
     pimp
    0.09
    _hide
    0.09
     damn
    0.09
     infusion
    0.09
    eus
    0.09
    Fuck
    0.09
     #$
    0.09
     FUCK
    0.08
    Activations Density 0.004%

    No Known Activations