© 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. 25534
    Prev
    Next
    INDEX
    Explanations

    anal, anus, admin, implant, colonic

    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
    naires
    -0.08
     torso
    -0.08
     Strip
    -0.08
    Abort
    -0.08
    egr
    -0.08
     Face
    -0.08
     hand
    -0.08
     Hodg
    -0.08
    erb
    -0.08
    adt
    -0.08
    POSITIVE LOGITS
     sph
    0.14
     anus
    0.13
     hole
    0.13
     Hole
    0.12
     fiss
    0.11
     gaping
    0.10
    hole
    0.10
    blick
    0.10
    ugas
    0.10
     Nat
    0.10
    Activations Density 0.006%

    No Known Activations