© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114054
    Prev
    Next
    INDEX
    Explanations

    masturbation habits

    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
    ardy
    -0.09
     astro
    -0.08
    iar
    -0.08
     multim
    -0.08
     Cha
    -0.08
    'We
    -0.08
     reunion
    -0.08
     takeover
    -0.08
     lear
    -0.08
    cheon
    -0.08
    POSITIVE LOGITS
     habits
    0.14
     habit
    0.12
     nightly
    0.12
     Habit
    0.12
    habit
    0.12
     solitary
    0.11
     Hab
    0.11
     habitual
    0.10
     daily
    0.10
     sessions
    0.09
    Activations Density 0.036%

    No Known Activations