© 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. 91283
    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
     beforehand
    -0.08
    arten
    -0.08
     absent
    -0.08
     Recover
    -0.08
    _spot
    -0.08
    /query
    -0.08
     recovering
    -0.07
     MEP
    -0.07
    issan
    -0.07
     retros
    -0.07
    POSITIVE LOGITS
     Bow
    0.11
    ï¼ŀ
    0.10
    elin
    0.10
    oble
    0.10
     bow
    0.10
    ocol
    0.10
     habit
    0.10
    atab
    0.10
     lul
    0.10
    aped
    0.10
    Activations Density 0.000%

    No Known Activations