© 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. 28839
    Prev
    Next
    INDEX
    Explanations

    audio recordings

    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
    _watch
    -0.12
     Visible
    -0.12
     visible
    -0.12
    Watching
    -0.11
    olut
    -0.11
     cinemat
    -0.11
     watching
    -0.10
     TV
    -0.10
    Visible
    -0.10
     photographers
    -0.10
    POSITIVE LOGITS
     audio
    0.39
     recordings
    0.37
     listeners
    0.34
     listener
    0.34
     voice
    0.34
     Audio
    0.33
     audi
    0.33
     audible
    0.32
     podcast
    0.31
     voices
    0.31
    Activations Density 0.630%

    No Known Activations