© 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. 14302
    Prev
    Next
    INDEX
    Explanations

    apparatus and methods

    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
     prostitution
    -0.19
    Prostit
    -0.16
     prostitutes
    -0.16
     Prostit
    -0.15
     street
    -0.14
     prostitute
    -0.14
     Escorts
    -0.14
     broth
    -0.14
     prostitu
    -0.14
     booking
    -0.13
    POSITIVE LOGITS
     Cabr
    0.10
    zilla
    0.10
     Avery
    0.10
     dik
    0.09
     Gamer
    0.09
    orr
    0.08
     Classroom
    0.08
     concussion
    0.08
     Voters
    0.08
    Sync
    0.08
    Activations Density 0.247%

    No Known Activations