© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 25725
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    sty
    -0.11
    AMS
    -0.10
     Dorm
    -0.09
     asses
    -0.09
     sok
    -0.09
     withheld
    -0.09
     aimed
    -0.09
     reassure
    -0.09
    vinc
    -0.09
    arie
    -0.09
    POSITIVE LOGITS
     Stella
    0.09
     Nav
    0.09
     Hit
    0.08
    nav
    0.08
    hetto
    0.07
    oplay
    0.07
    kes
    0.07
     Hanna
    0.07
     HDF
    0.07
     hitch
    0.07
    Activations Density 0.000%

    No Known Activations