© 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. 28693
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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
     sok
    -0.09
     Kern
    -0.09
     FAQs
    -0.09
    Agents
    -0.08
     unh
    -0.08
     twitter
    -0.08
     minib
    -0.08
    barang
    -0.08
     Twitter
    -0.08
    "_
    -0.08
    POSITIVE LOGITS
    <|endoftext|>
    0.19
    gmail
    0.10
    iez
    0.10
    Flag
    0.09
     disadv
    0.09
    ":""
    0.09
     favour
    0.09
     ure
    0.08
    22
    0.08
     favor
    0.08
    Activations Density 0.008%

    No Known Activations