© 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. 32504
    Prev
    Next
    INDEX
    Explanations

    voices 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
     conce
    -0.11
     Wand
    -0.10
     heaters
    -0.10
    uC
    -0.10
     Hog
    -0.10
    asco
    -0.09
     hangs
    -0.09
    _cv
    -0.09
     Setter
    -0.09
     prec
    -0.09
    POSITIVE LOGITS
     voices
    0.18
     whisper
    0.18
     voice
    0.17
     whispers
    0.16
     whispered
    0.14
    声
    0.13
    voice
    0.13
     sounding
    0.13
     Voices
    0.13
     nag
    0.13
    Activations Density 0.040%

    No Known Activations