© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32001
    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
    adle
    -0.11
    -dom
    -0.10
     Bender
    -0.10
    lok
    -0.10
    /dom
    -0.10
     dok
    -0.09
     rehabilit
    -0.09
     pac
    -0.09
     receptions
    -0.09
    /message
    -0.09
    POSITIVE LOGITS
    atten
    0.11
    ost
    0.10
    sted
    0.09
     Rowe
    0.09
    WO
    0.09
    anna
    0.08
    zu
    0.08
    olle
    0.08
     Dew
    0.08
    Super
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.