© 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. 115589
    Prev
    Next
    INDEX
    Explanations

    previous years

    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
    hest
    -0.10
     Rus
    -0.09
     somebody
    -0.09
    chin
    -0.09
    itz
    -0.08
    èª
    -0.08
    kas
    -0.08
     Geh
    -0.08
    ighting
    -0.08
     Muj
    -0.08
    POSITIVE LOGITS
     previous
    0.26
     countless
    0.24
     preceding
    0.22
    previous
    0.19
     predecessors
    0.19
     others
    0.18
    Previous
    0.17
     Previous
    0.17
     past
    0.15
    _previous
    0.14
    Activations Density 0.052%

    No Known Activations