© 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. 18093
    Prev
    Next
    INDEX
    Explanations

    uh, um, erm, er

    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
     Italia
    -0.10
     halfway
    -0.10
     bureauc
    -0.09
    OI
    -0.09
     laz
    -0.09
     flesh
    -0.09
     PIO
    -0.08
    ~↵
    -0.08
    (~
    -0.08
    252
    -0.08
    POSITIVE LOGITS
     uh
    0.31
     um
    0.30
     Um
    0.26
    Um
    0.25
     erm
    0.24
     Uh
    0.23
    Uh
    0.20
     er
    0.20
    um
    0.19
    ...
    0.19
    Activations Density 0.020%

    No Known Activations