© 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. 46803
    Prev
    Next
    INDEX
    Explanations

    anal angel

    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
     inve
    -0.08
     limb
    -0.08
     temper
    -0.08
     proprietor
    -0.08
    Creators
    -0.08
     conj
    -0.08
    -ton
    -0.08
     stern
    -0.08
     uncon
    -0.08
     clin
    -0.08
    POSITIVE LOGITS
     worship
    0.14
     worsh
    0.13
    /stat
    0.12
     Worship
    0.12
     slaves
    0.12
     swallowing
    0.11
     slave
    0.11
    .gca
    0.11
    serv
    0.10
     serviced
    0.10
    Activations Density 0.009%

    No Known Activations