© 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. 47107
    Prev
    Next
    INDEX
    Explanations

    example, sad, problem

    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
     behaviours
    -0.14
     cosy
    -0.14
     LGBTQ
    -0.13
     âĿ¤
    -0.13
     teen
    -0.12
     colour
    -0.12
     specialised
    -0.12
     fandom
    -0.12
     behaviour
    -0.11
    âĢķ
    -0.11
    POSITIVE LOGITS
     retarded
    0.16
     haha
    0.16
     dont
    0.14
     didnt
    0.14
     offseason
    0.13
     doesnt
    0.13
     ****
    0.13
     raping
    0.13
    dont
    0.13
     anyways
    0.13
    Activations Density 2.632%

    No Known Activations