© 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. 31932
    Prev
    Next
    INDEX
    Explanations

    audio and sound effects

    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
     vide
    -0.11
     Video
    -0.11
     phot
    -0.11
    /cloud
    -0.10
     video
    -0.10
     aggrav
    -0.10
     Phot
    -0.10
     Vide
    -0.10
     visually
    -0.10
     Videos
    -0.09
    POSITIVE LOGITS
     Dol
    0.14
     stereo
    0.14
     sound
    0.13
     surround
    0.13
     mono
    0.13
     SOUND
    0.12
    Ster
    0.12
     Stereo
    0.11
     Mono
    0.11
    sound
    0.11
    Activations Density 0.080%

    No Known Activations