© 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. 90967
    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
     formal
    -0.07
    nock
    -0.06
    omorphic
    -0.06
    inja
    -0.06
     explic
    -0.06
    ade
    -0.06
    iad
    -0.06
     Fisher
    -0.06
    imus
    -0.06
     lying
    -0.06
    POSITIVE LOGITS
    _DS
    0.13
     centrally
    0.12
    OUCH
    0.12
     Hyp
    0.12
    -shared
    0.11
     Pag
    0.11
     Rodney
    0.11
     Blow
    0.11
     Gate
    0.11
     Bergen
    0.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.