© 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. 115056
    Prev
    Next
    INDEX
    Explanations

    connecting things with lines or ropes

    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
    ouri
    -0.11
     nurs
    -0.11
     faces
    -0.10
     claw
    -0.10
     Size
    -0.10
    nar
    -0.10
    enis
    -0.10
     Weiner
    -0.10
     Lock
    -0.09
     lock
    -0.09
    POSITIVE LOGITS
     lengths
    0.16
     severed
    0.15
     bundles
    0.14
     slack
    0.14
     eman
    0.14
     draped
    0.13
     tension
    0.13
     stretched
    0.13
     connecting
    0.13
     bundle
    0.13
    Activations Density 0.321%

    No Known Activations