© 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. 47868
    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
     forb
    -0.10
     credential
    -0.10
    ysz
    -0.10
    hausen
    -0.09
     drawing
    -0.09
     flap
    -0.09
     fro
    -0.08
    mal
    -0.08
    StringBuilder
    -0.08
    ugu
    -0.08
    POSITIVE LOGITS
     Bü
    0.11
    remen
    0.10
    clr
    0.10
     intersect
    0.09
     Sass
    0.09
     blat
    0.09
    urat
    0.09
    eken
    0.09
     intersects
    0.09
    VERY
    0.09
    Activations Density 0.000%

    No Known Activations