© 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. 116911
    Prev
    Next
    INDEX
    Explanations

    no organization or unsafe

    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
    807
    -0.09
    ouser
    -0.09
    169
    -0.08
     shaped
    -0.08
    RM
    -0.08
    apat
    -0.08
     continuation
    -0.08
    gee
    -0.08
    ì¶
    -0.08
    Quiet
    -0.08
    POSITIVE LOGITS
     spared
    0.17
     sacred
    0.17
     safe
    0.15
     sanctuary
    0.14
     unreachable
    0.14
     unsafe
    0.14
     escapes
    0.14
     limits
    0.13
     escape
    0.13
     sac
    0.13
    Activations Density 0.078%

    No Known Activations