© 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. 4830
    Prev
    Next
    INDEX
    Explanations

    075, 001, 051, 204, 257

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    09
    -0.12
    00
    -0.12
    08
    -0.11
    19
    -0.11
    07
    -0.10
    34
    -0.10
    49
    -0.10
    41
    -0.10
    01
    -0.10
    29
    -0.10
    POSITIVE LOGITS
    196
    0.16
    200
    0.15
    197
    0.15
    195
    0.15
    198
    0.14
     hundreds
    0.14
    250
    0.14
    194
    0.14
    177
    0.13
    193
    0.13
    Activations Density 0.725%

    No Known Activations