© 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. 6871
    Prev
    Next
    INDEX
    Explanations

    medical or permissions related text

    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
     wat
    -0.10
     Phon
    -0.10
    èIJ
    -0.09
     phon
    -0.09
     Penguins
    -0.08
     polluted
    -0.08
     Volley
    -0.08
     Hearth
    -0.08
     optical
    -0.08
    esk
    -0.08
    POSITIVE LOGITS
     BDSM
    0.15
     bdsm
    0.12
     bruises
    0.11
     Consent
    0.11
     safer
    0.11
     mainstream
    0.11
     Dover
    0.11
     Cru
    0.11
    orum
    0.10
     bru
    0.10
    Activations Density 0.164%

    No Known Activations