© 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. 114330
    Prev
    Next
    INDEX
    Explanations

    without notice or warning; unannounced

    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
    ander
    -0.11
    ucha
    -0.11
    hart
    -0.11
     willingly
    -0.11
    credible
    -0.11
     needless
    -0.11
     threatening
    -0.11
    ooter
    -0.11
     Heller
    -0.11
     fellowship
    -0.11
    POSITIVE LOGITS
     whatsoever
    0.14
    tot
    0.10
     WHATSOEVER
    0.09
     pregnancies
    0.08
     BAM
    0.08
     thrust
    0.08
    ed
    0.08
    ly
    0.08
    /un
    0.08
     nor
    0.08
    Activations Density 0.002%

    No Known Activations