© 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. 115154
    Prev
    Next
    INDEX
    Explanations

    sudden impact sounds

    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
     zwar
    -0.13
    upplier
    -0.10
     organising
    -0.10
    ffa
    -0.10
    eba
    -0.10
     Tried
    -0.10
    ONA
    -0.10
     extreme
    -0.09
    ston
    -0.09
    /me
    -0.09
    POSITIVE LOGITS
     BAM
    0.15
     vo
    0.15
     boom
    0.14
     bam
    0.14
     Boom
    0.13
     suddenly
    0.13
     finally
    0.13
     bingo
    0.12
    Boom
    0.11
    –↵↵
    0.11
    Activations Density 0.028%

    No Known Activations