© 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. 26236
    Prev
    Next
    INDEX
    Explanations

    basement, cellar, dungeon, shop, warehouse

    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
     umb
    -0.10
     flirt
    -0.10
     conversation
    -0.10
     terminals
    -0.09
    spy
    -0.09
     flirting
    -0.09
     libr
    -0.09
     Sax
    -0.09
     SYS
    -0.09
     NPR
    -0.09
    POSITIVE LOGITS
     basement
    0.18
     Basement
    0.14
     dungeon
    0.14
     specially
    0.13
     warehouse
    0.12
     cellar
    0.12
     delimited
    0.11
     rigged
    0.11
     Slave
    0.11
     BDSM
    0.11
    Activations Density 0.024%

    No Known Activations