© 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. 89546
    Prev
    Next
    INDEX
    Explanations

    get away with actions

    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
    PIO
    -0.13
     incons
    -0.12
    ẩm
    -0.11
     earm
    -0.10
     Wig
    -0.10
    rez
    -0.10
     dou
    -0.10
     Vine
    -0.10
    chy
    -0.10
    rlen
    -0.10
    POSITIVE LOGITS
     murder
    0.18
     Murder
    0.12
    ably
    0.11
     robbery
    0.09
     homicide
    0.09
     crimes
    0.08
     treating
    0.08
    (es
    0.08
     being
    0.08
    Answers
    0.08
    Activations Density 0.005%

    No Known Activations