© 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. 89743
    Prev
    Next
    INDEX
    Explanations

    auditory or audition or audit

    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
     Colum
    -0.10
     hast
    -0.09
     Mixed
    -0.08
    atcher
    -0.08
    alk
    -0.08
     Flake
    -0.08
     flawless
    -0.08
     fol
    -0.08
     rich
    -0.08
    ant
    -0.08
    POSITIVE LOGITS
    ibly
    0.14
    ible
    0.14
     invis
    0.13
     audible
    0.13
     visible
    0.12
    iences
    0.12
    ibility
    0.11
    Visible
    0.11
     invisible
    0.11
     unintention
    0.11
    Activations Density 0.002%

    No Known Activations