© 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. 113546
    Prev
    Next
    INDEX
    Explanations

    will be posting

    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
     already
    -0.10
     thanks
    -0.09
     anticipation
    -0.09
     anticip
    -0.09
     inspir
    -0.09
     inspiration
    -0.08
     impatient
    -0.08
     anticipating
    -0.08
     brainstorm
    -0.08
    nel
    -0.08
    POSITIVE LOGITS
     eventually
    0.18
     periodically
    0.17
     posting
    0.16
     postings
    0.16
     Eventually
    0.15
     posts
    0.14
     periodic
    0.14
     eventual
    0.14
     Posting
    0.13
     progressively
    0.13
    Activations Density 0.246%

    No Known Activations