© 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. 5899
    Prev
    Next
    INDEX
    Explanations

    way through or to

    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
     deeply
    -0.10
    onga
    -0.09
     Rentals
    -0.08
     OC
    -0.08
     firstly
    -0.08
     boiled
    -0.08
     déjÃł
    -0.08
    bz
    -0.08
     Nie
    -0.08
     Consortium
    -0.08
    POSITIVE LOGITS
     throughout
    0.20
     until
    0.16
     into
    0.16
     everywhere
    0.15
     across
    0.14
    into
    0.14
     till
    0.14
     through
    0.13
     onto
    0.13
     Throughout
    0.13
    Activations Density 0.089%

    No Known Activations