© 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. 27464
    Prev
    Next
    INDEX
    Explanations

    started a

    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
     peek
    -0.11
     porte
    -0.10
    iste
    -0.10
    peek
    -0.10
     triumph
    -0.10
    ìĥģ
    -0.09
    419
    -0.09
     setback
    -0.09
     defeat
    -0.09
    emit
    -0.09
    POSITIVE LOGITS
     fires
    0.16
     conversation
    0.15
     thread
    0.14
     chain
    0.14
     conversations
    0.13
    conversation
    0.13
     dialogue
    0.13
     wars
    0.12
     chant
    0.12
     threads
    0.12
    Activations Density 0.182%

    No Known Activations