© 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. 91435
    Prev
    Next
    INDEX
    Explanations

    loudness and 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
    /do
    -0.12
    laus
    -0.10
     generalized
    -0.08
    loth
    -0.08
     protester
    -0.08
     Taste
    -0.08
     Orwell
    -0.08
     Mass
    -0.08
    awk
    -0.08
     crit
    -0.08
    POSITIVE LOGITS
     louder
    0.22
     loud
    0.18
     lou
    0.18
     shouting
    0.16
     Lou
    0.15
     volume
    0.14
    -volume
    0.14
     loudly
    0.14
    Lou
    0.14
     Loud
    0.14
    Activations Density 0.058%

    No Known Activations