© 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. 90804
    Prev
    Next
    INDEX
    Explanations

    sl + common word endings

    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
     Leg
    -0.09
     entert
    -0.09
     entertain
    -0.09
     Finch
    -0.09
    iren
    -0.08
     Nel
    -0.08
    rive
    -0.08
     Kle
    -0.08
    UNC
    -0.08
     entertaining
    -0.08
    POSITIVE LOGITS
     sl
    0.22
     slur
    0.18
    sl
    0.15
    -sl
    0.15
    /sl
    0.15
    (sl
    0.14
     slapped
    0.13
     Sl
    0.13
    	sl
    0.13
    Sl
    0.12
    Activations Density 0.009%

    No Known Activations