© 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. 6970
    Prev
    Next
    INDEX
    Explanations

    at once or at the same time

    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
     alike
    -0.14
     Mü
    -0.10
    ORA
    -0.10
     Voyage
    -0.10
     jointly
    -0.10
    ulan
    -0.09
    eson
    -0.09
     Patron
    -0.09
     Hodg
    -0.09
     timely
    -0.09
    POSITIVE LOGITS
    inth
    0.11
     Fut
    0.10
    /as
    0.10
    aneously
    0.10
    aneous
    0.10
    /place
    0.09
     Coff
    0.09
    aus
    0.09
     frame
    0.09
    /by
    0.09
    Activations Density 0.036%

    No Known Activations