© 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. 33135
    Prev
    Next
    INDEX
    Explanations

    joining together

    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
     Mare
    -0.11
     neither
    -0.09
     nin
    -0.09
     skies
    -0.09
     assignable
    -0.09
    jis
    -0.08
    NG
    -0.08
     inf
    -0.08
     caut
    -0.08
     hypoth
    -0.08
    POSITIVE LOGITS
     together
    0.50
     Together
    0.38
    Together
    0.35
    gether
    0.27
     zusammen
    0.22
     tog
    0.18
     disparate
    0.17
     pieces
    0.16
     assembled
    0.16
     sammen
    0.16
    Activations Density 0.379%

    No Known Activations