© 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. 33732
    Prev
    Next
    INDEX
    Explanations

    parody, critique, satire, sketch

    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
    inet
    -0.10
     Mum
    -0.10
     incompatible
    -0.10
    WATCH
    -0.09
     tot
    -0.09
    otify
    -0.09
    ported
    -0.09
    LY
    -0.09
    WO
    -0.09
     reckon
    -0.09
    POSITIVE LOGITS
    /mock
    0.17
    /comment
    0.13
     parody
    0.12
    /com
    0.12
     exagger
    0.12
    /exp
    0.11
     lamp
    0.10
     thereof
    0.10
    /ex
    0.10
     poke
    0.10
    Activations Density 0.023%

    No Known Activations