© 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. 115180
    Prev
    Next
    INDEX
    Explanations

    voice and sound qualities

    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
     Visible
    -0.12
     visible
    -0.11
    _visible
    -0.11
    vero
    -0.10
    loom
    -0.10
    Visible
    -0.10
     loin
    -0.10
     parce
    -0.10
    reff
    -0.10
     mentality
    -0.10
    POSITIVE LOGITS
     voice
    0.19
     voices
    0.18
     sounded
    0.18
     sounds
    0.18
     sounding
    0.17
     Voices
    0.16
     pleasant
    0.15
     sound
    0.15
     tones
    0.15
    声
    0.15
    Activations Density 0.041%

    No Known Activations