© 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. 26169
    Prev
    Next
    INDEX
    Explanations

    sounds, bells, and events

    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
     Locker
    -0.13
     Leak
    -0.13
    (.)
    -0.13
    locker
    -0.13
    agas
    -0.12
     GURL
    -0.11
    itel
    -0.11
    ZH
    -0.11
    HG
    -0.11
     oltre
    -0.11
    POSITIVE LOGITS
     loudly
    0.10
     indicating
    0.08
     softly
    0.08
    indic
    0.08
    ows
    0.08
     announcing
    0.08
     welcoming
    0.07
    imes
    0.07
    ety
    0.07
     inviting
    0.07
    Activations Density 0.005%

    No Known Activations