© 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. 15249
    Prev
    Next
    INDEX
    Explanations

    talk

    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
    kar
    -0.07
     Nos
    -0.07
     Inquiry
    -0.06
     Alt
    -0.06
    ently
    -0.06
     obt
    -0.06
    Ìģ
    -0.06
     out
    -0.06
     Few
    -0.06
     uncont
    -0.06
    POSITIVE LOGITS
     Talk
    0.20
    talk
    0.20
     talk
    0.17
    Talk
    0.17
    -talk
    0.17
    swith
    0.17
    er
    0.16
     Talks
    0.15
     talks
    0.15
    ative
    0.14
    Activations Density 0.026%

    No Known Activations