© 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. 27869
    Prev
    Next
    INDEX
    Explanations

    liquid followed by a noun

    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
    ingly
    -0.10
    ington
    -0.09
    lessly
    -0.09
    ening
    -0.08
    ugh
    -0.08
    ing
    -0.08
     Mog
    -0.08
    adge
    -0.08
    rego
    -0.08
     Swamp
    -0.08
    POSITIVE LOGITS
    ated
    0.15
    keiten
    0.13
    ation
    0.13
    ized
    0.12
    amber
    0.12
    ators
    0.12
    faction
    0.12
    ating
    0.11
    -phase
    0.11
    -solid
    0.11
    Activations Density 0.024%

    No Known Activations