© 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. 32363
    Prev
    Next
    INDEX
    Explanations

    introducing a point or opinion

    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
    HEY
    -0.10
     physically
    -0.10
     legally
    -0.10
     sexually
    -0.10
     grooming
    -0.09
    /activity
    -0.09
     groom
    -0.09
     prostitu
    -0.09
     realistically
    -0.09
     unspecified
    -0.09
    POSITIVE LOGITS
     provocative
    0.17
     provoc
    0.16
     unpack
    0.15
     synthes
    0.13
     nood
    0.13
     straw
    0.12
     tent
    0.12
     riff
    0.12
     tease
    0.12
     precis
    0.12
    Activations Density 2.456%

    No Known Activations