© 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. 27203
    Prev
    Next
    INDEX
    Explanations

    of [entity/concept]

    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
    andel
    -0.11
    osten
    -0.10
    481
    -0.10
     reins
    -0.10
     stew
    -0.09
     Athe
    -0.09
    imir
    -0.09
    ipt
    -0.09
    probe
    -0.09
    mil
    -0.09
    POSITIVE LOGITS
    ies
    0.10
    aha
    0.08
     accordingly
    0.08
    ayan
    0.08
    cia
    0.08
    /topics
    0.08
     Rounded
    0.08
    icie
    0.08
    weg
    0.07
    ied
    0.07
    Activations Density 0.004%

    No Known Activations