© 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. 33724
    Prev
    Next
    INDEX
    Explanations

    not serious, stiff, solemn

    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
     irresponsible
    -0.13
     laz
    -0.12
     procrast
    -0.11
     mutil
    -0.11
     humiliation
    -0.11
     humili
    -0.10
     careless
    -0.10
     degradation
    -0.10
     deceptive
    -0.10
     lazy
    -0.10
    POSITIVE LOGITS
     rigid
    0.26
     upt
    0.25
     seriousness
    0.23
     stiff
    0.22
     solemn
    0.21
     stern
    0.19
     strict
    0.19
     stricter
    0.19
     Serious
    0.18
     pomp
    0.18
    Activations Density 0.146%

    No Known Activations