© 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. 16530
    Prev
    Next
    INDEX
    Explanations

    cognitive skills or thinking properly

    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
     unofficial
    -0.13
     impuls
    -0.11
    istes
    -0.10
     insufficient
    -0.09
     blind
    -0.09
     reluctantly
    -0.09
    blind
    -0.09
     Cand
    -0.09
     Dude
    -0.09
     implic
    -0.09
    POSITIVE LOGITS
     coherent
    0.23
     coherence
    0.17
     cohesive
    0.16
     intellig
    0.15
     articulate
    0.15
     anything
    0.15
     properly
    0.14
     artic
    0.14
     functioning
    0.13
     correctly
    0.12
    Activations Density 0.039%

    No Known Activations