© 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. 90622
    Prev
    Next
    INDEX
    Explanations

    starting or start

    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
    anni
    -0.10
     maxX
    -0.09
     timely
    -0.09
     reun
    -0.09
    _ax
    -0.09
    vat
    -0.09
     haut
    -0.09
     saber
    -0.09
    åĬŁ
    -0.08
    ond
    -0.08
    POSITIVE LOGITS
     starting
    0.50
     start
    0.47
     Start
    0.44
     starts
    0.41
     Starting
    0.40
    Start
    0.39
    starting
    0.38
     START
    0.38
    start
    0.38
    -start
    0.38
    Activations Density 0.206%

    No Known Activations