© 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. 32416
    Prev
    Next
    INDEX
    Explanations

    medium.com URIs

    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
     –
    -0.10
     hors
    -0.09
    itol
    -0.09
    wyn
    -0.09
    PCS
    -0.09
    agon
    -0.09
    -'
    -0.09
     [=
    -0.09
    "http
    -0.09
     DVDs
    -0.09
    POSITIVE LOGITS
     Medium
    0.25
     ðŁij
    0.21
    medium
    0.19
     medium
    0.19
    Medium
    0.19
     ðŁ
    0.17
     ðŁĶ
    0.16
    .medium
    0.16
    ðŁ
    0.16
    ï¸ı
    0.15
    Activations Density 0.810%

    No Known Activations