© 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. 112646
    Prev
    Next
    INDEX
    Explanations

    cutting body parts

    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
    Deg
    -0.10
    unci
    -0.09
     Deg
    -0.09
     degradation
    -0.09
     injury
    -0.08
     degraded
    -0.08
    erd
    -0.08
     cleansing
    -0.08
     trunc
    -0.08
     trauma
    -0.08
    POSITIVE LOGITS
     limbs
    0.21
     bones
    0.21
     organs
    0.21
     eyeb
    0.21
     kidneys
    0.19
     intest
    0.18
    bones
    0.17
     flesh
    0.16
     lungs
    0.16
     arms
    0.15
    Activations Density 0.131%

    No Known Activations