© 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. 30117
    Prev
    Next
    INDEX
    Explanations

    the [normal/usual/details/benefits/options]

    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
     fortunes
    -0.08
    sters
    -0.08
     Shore
    -0.08
    quet
    -0.08
     Shepherd
    -0.08
     Scre
    -0.08
    fahren
    -0.08
     veil
    -0.08
    ree
    -0.07
    cheng
    -0.07
    POSITIVE LOGITS
     usual
    0.14
     hall
    0.13
     earm
    0.12
     detail
    0.12
    SAME
    0.12
     trop
    0.11
     mak
    0.11
     bö
    0.11
     qualities
    0.11
     trim
    0.11
    Activations Density 0.033%

    No Known Activations