© 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. 14912
    Prev
    Next
    INDEX
    Explanations

    mind or thoughts

    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
    ussen
    -0.11
    amel
    -0.10
    Marco
    -0.10
    unsupported
    -0.09
     TK
    -0.09
    lyn
    -0.09
     Baz
    -0.08
     Dich
    -0.08
     Marco
    -0.08
    lingen
    -0.08
    POSITIVE LOGITS
     minded
    0.19
     thoughts
    0.18
    -minded
    0.18
     agenda
    0.16
     intentions
    0.16
     priorities
    0.16
     priority
    0.15
     Thoughts
    0.14
     mindset
    0.14
     intent
    0.14
    Activations Density 0.059%

    No Known Activations