© 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. 89931
    Prev
    Next
    INDEX
    Explanations

    raid, AAF, Hague, bait

    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
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.10
     fate
    -0.10
    ality
    -0.10
    ally
    -0.09
    ised
    -0.09
    pane
    -0.09
    ihat
    -0.09
    amines
    -0.09
    ¡°
    -0.09
    eated
    -0.08
    POSITIVE LOGITS
    fully
    0.15
    ın
    0.13
    erness
    0.10
    fulness
    0.10
    IGH
    0.10
    eworthy
    0.10
     href
    0.09
    nable
    0.09
    iflower
    0.09
    forth
    0.09
    Activations Density 0.346%

    No Known Activations