© 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. 33024
    Prev
    Next
    INDEX
    Explanations

    blood and bleeding

    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
     bree
    -0.10
    coal
    -0.10
     cache
    -0.10
     cuck
    -0.10
    TN
    -0.09
     lul
    -0.09
    _cache
    -0.09
     Buen
    -0.09
     wildfire
    -0.09
     fires
    -0.09
    POSITIVE LOGITS
     blood
    0.63
     Blood
    0.58
    Blood
    0.53
    blood
    0.50
     bloody
    0.50
     bleeding
    0.48
    -blood
    0.44
     Bloody
    0.43
     bleed
    0.43
     hemat
    0.38
    Activations Density 1.272%

    No Known Activations