© 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. 88957
    Prev
    Next
    INDEX
    Explanations

    what I mean

    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
     what
    -0.11
     flushed
    -0.09
    what
    -0.09
     incons
    -0.08
     Arcade
    -0.08
    ODE
    -0.08
     Reb
    -0.07
    .Trace
    -0.07
     bod
    -0.07
     patron
    -0.07
    POSITIVE LOGITS
     I
    0.16
     Im
    0.11
     yourselves
    0.10
    etz
    0.10
     targ
    0.10
    ál
    0.10
    172
    0.10
    ouri
    0.09
    ampus
    0.09
     yourself
    0.09
    Activations Density 0.011%

    No Known Activations