© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 17675
    Prev
    Next
    INDEX
    Explanations

    reporting events or actions

    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
    isc
    -0.09
    elles
    -0.09
    204
    -0.08
    rab
    -0.08
    233
    -0.08
    walker
    -0.08
    ROUT
    -0.07
    sonian
    -0.07
    åĪĨ
    -0.07
    nia
    -0.07
    POSITIVE LOGITS
     someone
    0.22
     Someone
    0.21
     somebody
    0.21
    Someone
    0.18
     Suddenly
    0.18
     another
    0.17
     Somebody
    0.17
    someone
    0.17
     suddenly
    0.15
    Suddenly
    0.15
    Activations Density 0.285%

    No Known Activations