© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 29603
    Prev
    Next
    INDEX
    Explanations

    unused, inactive, dormant

    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
    adh
    -0.10
     improvised
    -0.09
     fuzz
    -0.09
     amplified
    -0.09
    volatile
    -0.09
     rebuilt
    -0.09
     Hague
    -0.09
     augmented
    -0.08
     reun
    -0.08
    usi
    -0.08
    POSITIVE LOGITS
     unused
    0.43
     Unused
    0.33
     dormant
    0.31
    Unused
    0.30
     untouched
    0.29
    unused
    0.29
     UNUSED
    0.29
     idle
    0.27
     inactive
    0.27
    _unused
    0.22
    Activations Density 0.419%

    No Known Activations