© 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. 17165
    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
    _cleanup
    -0.08
     Newman
    -0.08
     eccentric
    -0.08
     imb
    -0.08
    -flag
    -0.08
    OPT
    -0.08
     unin
    -0.08
     choose
    -0.08
    аннÑĭ
    -0.07
     enclosed
    -0.07
    POSITIVE LOGITS
    eldo
    0.11
     Oper
    0.11
    Oper
    0.11
    urat
    0.10
     }:
    0.10
     operates
    0.10
    GH
    0.10
    asa
    0.10
     Relay
    0.10
    thinkable
    0.10
    Activations Density 0.000%

    No Known Activations