© 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. 27740
    Prev
    Next
    INDEX
    Explanations

    delete

    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
     overturned
    -0.11
    Abr
    -0.11
     Bray
    -0.10
     inertia
    -0.10
     dif
    -0.10
     lut
    -0.10
     splitted
    -0.10
     collaps
    -0.10
    abbrev
    -0.09
    Cel
    -0.09
    POSITIVE LOGITS
    åĪłéĻ¤æĪIJåĬŁ
    0.14
     delete
    0.14
     deleting
    0.14
     deletes
    0.14
    åĪłéĻ¤
    0.13
     delet
    0.13
    (delete
    0.13
     åĪłéĻ¤
    0.13
     deletion
    0.12
    .delete
    0.12
    Activations Density 0.188%

    No Known Activations