© 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. 91383
    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
     multis
    -0.09
     Psi
    -0.09
     Nah
    -0.09
     vehement
    -0.09
    DBG
    -0.08
    WF
    -0.08
     killer
    -0.08
    wf
    -0.08
    raf
    -0.08
     nah
    -0.08
    POSITIVE LOGITS
     Morr
    0.10
    ala
    0.10
    ALA
    0.10
     flakes
    0.10
     ald
    0.10
     kilomet
    0.10
    atak
    0.10
    asca
    0.10
    XmlElement
    0.09
     ($)
    0.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.