© 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. 116825
    Prev
    Next
    INDEX
    Explanations

    dog leash or collar

    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
     smugg
    -0.11
     smuggling
    -0.10
     Fever
    -0.10
     inaug
    -0.09
     recurse
    -0.09
     solvent
    -0.09
     smear
    -0.08
     pore
    -0.08
    dal
    -0.08
     ripping
    -0.08
    POSITIVE LOGITS
     leash
    0.45
     tether
    0.40
     chained
    0.29
     chains
    0.25
     chain
    0.24
     chaining
    0.24
     Chain
    0.23
     collar
    0.23
    -chain
    0.23
     Chains
    0.20
    Activations Density 0.126%

    No Known Activations