© 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. 47836
    Prev
    Next
    INDEX
    Explanations

    magic special effects

    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
    gens
    -0.08
    /wiki
    -0.08
    /software
    -0.08
    stalk
    -0.07
     caut
    -0.07
     erot
    -0.07
     nudity
    -0.07
    wide
    -0.07
    Scoped
    -0.07
    agua
    -0.07
    POSITIVE LOGITS
     videos
    0.15
     fetish
    0.15
     specialist
    0.14
     scenes
    0.14
     scene
    0.14
    /stretch
    0.13
     performed
    0.13
     specialists
    0.13
    -heavy
    0.13
     Specialists
    0.13
    Activations Density 0.101%

    No Known Activations