© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 4653
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     infra
    -0.10
     Roy
    -0.08
    aber
    -0.08
     vale
    -0.08
     kino
    -0.08
    iates
    -0.08
     allerg
    -0.07
    ITH
    -0.07
    pollo
    -0.07
    oki
    -0.07
    POSITIVE LOGITS
     judgement
    0.13
     judgment
    0.12
     wom
    0.12
     slut
    0.11
    icio
    0.11
     Mut
    0.10
     gossip
    0.10
     repro
    0.10
    -chan
    0.10
    iaux
    0.10
    Activations Density 0.000%

    No Known Activations