© 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. 29321
    Prev
    Next
    INDEX
    Explanations

    eliminating, freeing, or reducing

    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
    eks
    -0.09
    ICS
    -0.09
     unconditional
    -0.08
    IAS
    -0.08
    fun
    -0.08
     Ul
    -0.08
    ulk
    -0.08
    iza
    -0.08
    á
    -0.08
     fam
    -0.08
    POSITIVE LOGITS
     rid
    0.23
     eliminating
    0.15
     freeing
    0.14
     fewer
    0.14
     Freed
    0.14
     Elim
    0.13
     elimination
    0.13
     eliminates
    0.13
     eliminate
    0.13
     frankly
    0.13
    Activations Density 0.104%

    No Known Activations