© 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. 32063
    Prev
    Next
    INDEX
    Explanations

    Jon followed by names

    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
    ëĭ¹
    -0.12
     Mate
    -0.10
     flashes
    -0.10
     McCabe
    -0.10
    venge
    -0.09
    onta
    -0.09
    vore
    -0.09
    osi
    -0.09
    pton
    -0.09
    pite
    -0.09
    POSITIVE LOGITS
    athon
    0.21
    ny
    0.14
    ATH
    0.13
    quil
    0.13
    atan
    0.13
    assen
    0.12
     Snow
    0.12
    atha
    0.11
    ath
    0.11
    athan
    0.10
    Activations Density 0.016%

    No Known Activations