© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113968
    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
     suspended
    -0.11
     Idle
    -0.10
     detached
    -0.10
    modo
    -0.10
     Susp
    -0.10
     Roy
    -0.09
    backs
    -0.09
     similarly
    -0.09
     incumbent
    -0.09
    924
    -0.09
    POSITIVE LOGITS
     defiant
    0.09
    oin
    0.08
    FM
    0.08
    pub
    0.08
     Checkout
    0.08
     marathon
    0.08
     br
    0.08
     Hayes
    0.08
     stagger
    0.08
    CES
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.