© 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. 117067
    Prev
    Next
    INDEX
    Explanations

    at a rate

    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
    icht
    -0.11
     bump
    -0.10
     coff
    -0.10
     bitterness
    -0.09
     nich
    -0.09
    377
    -0.09
    loe
    -0.09
     manoe
    -0.09
     interf
    -0.09
    ichtig
    -0.09
    POSITIVE LOGITS
     pace
    0.17
     Pace
    0.16
     speeds
    0.15
     rates
    0.15
     rate
    0.13
     angles
    0.12
     speed
    0.11
     heights
    0.11
     levels
    0.11
     intervals
    0.11
    Activations Density 0.172%

    No Known Activations