© 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. 115458
    Prev
    Next
    INDEX
    Explanations

    Unity asset identifiers or numbered references

    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
    -minus
    -0.11
     Crowd
    -0.10
    onga
    -0.10
    altar
    -0.09
     Crowley
    -0.09
     Florian
    -0.09
    iri
    -0.09
    ifix
    -0.09
    adol
    -0.09
    isd
    -0.08
    POSITIVE LOGITS
    _INSTANCE
    0.10
     baj
    0.10
     CREATED
    0.09
     Bucc
    0.09
     spir
    0.09
    Creative
    0.09
     ot
    0.09
     mang
    0.09
    cul
    0.09
     jams
    0.09
    Activations Density 0.776%

    No Known Activations