© 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. 48914
    Prev
    Next
    INDEX
    Explanations

    worst or best comparisons

    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
     inverted
    -0.10
     ever
    -0.10
    argas
    -0.09
    vat
    -0.09
    ÑĢов
    -0.09
     EVER
    -0.09
    irs
    -0.09
    arov
    -0.09
    ât
    -0.09
    */}↵
    -0.09
    POSITIVE LOGITS
    done
    0.10
    -case
    0.09
     done
    0.09
     happening
    0.09
     happens
    0.09
     unsus
    0.08
     enjo
    0.08
     Vern
    0.08
    uta
    0.08
     of
    0.08
    Activations Density 0.008%

    No Known Activations