© 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. 27149
    Prev
    Next
    INDEX
    Explanations

    reach or reaching a limit

    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
    /respond
    -0.11
     clue
    -0.11
     Aber
    -0.11
    hoff
    -0.11
     drifting
    -0.10
     lingering
    -0.10
    azu
    -0.10
    primer
    -0.10
    /update
    -0.09
    /fire
    -0.09
    POSITIVE LOGITS
     reached
    0.16
     maturity
    0.15
     reaching
    0.14
     reach
    0.13
     reaches
    0.13
     Reach
    0.13
     Reached
    0.11
    Reach
    0.10
     puberty
    0.10
     infinity
    0.09
    Activations Density 0.003%

    No Known Activations