© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30023
    Prev
    Next
    INDEX
    Explanations

    apply, attach, add, build, wrap

    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
     Dt
    -0.09
    -clean
    -0.09
     Kra
    -0.09
     Andre
    -0.09
    privileged
    -0.09
     æ¸
    -0.08
     outdoors
    -0.08
     Increment
    -0.08
    handling
    -0.08
     defaults
    -0.08
    POSITIVE LOGITS
     taped
    0.17
     tape
    0.17
     hacks
    0.15
     wrapping
    0.15
     wrapped
    0.15
     masking
    0.14
     wrap
    0.14
     blocker
    0.14
     covers
    0.14
     wraps
    0.13
    Activations Density 0.614%

    No Known Activations