© 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. 49331
    Prev
    Next
    INDEX
    Explanations

    obsessive ritualistic behaviours

    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
     yourselves
    -0.12
     guts
    -0.11
     rhetorical
    -0.10
     virtues
    -0.10
     presum
    -0.10
     feminism
    -0.10
     radiant
    -0.10
     funky
    -0.10
    åĬŁ
    -0.10
    ernity
    -0.10
    POSITIVE LOGITS
     compuls
    0.26
     obsess
    0.18
     obsession
    0.17
     obsessive
    0.16
     fantas
    0.15
     sufferers
    0.15
     masturb
    0.15
     ritual
    0.15
     rituals
    0.14
     compelled
    0.14
    Activations Density 0.057%

    No Known Activations