© 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. 16600
    Prev
    Next
    INDEX
    Explanations

    sedative, induction, lure

    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
     Barth
    -0.11
     outs
    -0.11
    éĶĻ
    -0.10
    legen
    -0.10
     bog
    -0.10
    outs
    -0.10
     fret
    -0.10
     Gord
    -0.09
     summers
    -0.09
    akers
    -0.09
    POSITIVE LOGITS
    ively
    0.16
    ors
    0.13
    uctive
    0.10
    eer
    0.10
    /conf
    0.10
     charm
    0.10
    eur
    0.10
     lure
    0.10
    /mark
    0.09
     allure
    0.09
    Activations Density 0.006%

    No Known Activations