© 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. 17029
    Prev
    Next
    INDEX
    Explanations

    good, nice, pleasing, comforting

    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
    oux
    -0.13
     kommer
    -0.11
     contr
    -0.11
    openh
    -0.10
     independ
    -0.10
    ixer
    -0.10
     Merc
    -0.10
     hopeless
    -0.10
    open
    -0.10
    imens
    -0.10
    POSITIVE LOGITS
     pleasant
    0.31
     pleasing
    0.25
     comforting
    0.25
     soothing
    0.24
    pleasant
    0.24
     nice
    0.22
     enjoyable
    0.22
     Pleasant
    0.22
     pleasantly
    0.21
     comfortable
    0.21
    Activations Density 0.033%

    No Known Activations