© 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. 17025
    Prev
    Next
    INDEX
    Explanations

    ssh authentication

    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
     stag
    -0.11
    éré
    -0.09
     tep
    -0.09
    ourd
    -0.09
     dives
    -0.09
     sans
    -0.09
     schö
    -0.09
     break
    -0.09
    WO
    -0.08
    Styled
    -0.08
    POSITIVE LOGITS
    ude
    0.11
     Quiet
    0.10
     quiet
    0.09
    Quiet
    0.09
     Aur
    0.09
    -ing
    0.09
    udi
    0.09
    AMB
    0.08
     finger
    0.08
    quiet
    0.08
    Activations Density 0.002%

    No Known Activations