© 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. 48820
    Prev
    Next
    INDEX
    Explanations

    create callback listcreate programscreate captionscreate valuecreate passwordcreate variablescreate HTTP request

    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
     creative
    -0.15
     creativity
    -0.15
    creative
    -0.13
     constructed
    -0.12
     creations
    -0.12
     induced
    -0.12
    ynn
    -0.11
     creatively
    -0.11
    constructed
    -0.11
     Weston
    -0.11
    POSITIVE LOGITS
     deb
    0.09
     impression
    0.09
     effect
    0.08
     dag
    0.08
     sensation
    0.07
     Kemp
    0.07
     Shim
    0.07
    cir
    0.07
     latch
    0.07
     Checkout
    0.07
    Activations Density 0.482%

    No Known Activations