© 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. 16202
    Prev
    Next
    INDEX
    Explanations

    heat and charge transport

    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
     Duis
    -0.10
    /window
    -0.09
     tuned
    -0.09
     twitch
    -0.08
     fright
    -0.08
     Whe
    -0.08
     aud
    -0.08
    -hover
    -0.08
    tie
    -0.08
     Helena
    -0.08
    POSITIVE LOGITS
     diss
    0.11
    gow
    0.10
    jac
    0.10
    bk
    0.10
     dissip
    0.09
     fins
    0.09
    Signature
    0.09
     friction
    0.09
     ðŁĶ
    0.09
    signature
    0.09
    Activations Density 0.095%

    No Known Activations