© 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. 27021
    Prev
    Next
    INDEX
    Explanations

    instructions and conditions

    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
     frankly
    -0.16
     IMO
    -0.14
     obviously
    -0.13
     fortunately
    -0.13
     luckily
    -0.12
     admittedly
    -0.12
     evidently
    -0.12
     Sof
    -0.11
     kne
    -0.11
     Sergio
    -0.11
    POSITIVE LOGITS
     ALWAYS
    0.11
     always
    0.09
     NOT
    0.08
     ONLY
    0.08
     vet
    0.08
     ALL
    0.08
    Always
    0.07
    /=
    0.07
     Always
    0.07
    ctp
    0.07
    Activations Density 0.116%

    No Known Activations