© 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. 112916
    Prev
    Next
    INDEX
    Explanations

    authorsworkpublications

    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
     DK
    -0.09
    ited
    -0.09
    tn
    -0.09
     Kidd
    -0.09
     Dat
    -0.09
     Kal
    -0.09
    LANG
    -0.09
    GD
    -0.09
     bt
    -0.08
     Mandal
    -0.08
    POSITIVE LOGITS
    arbeit
    0.08
     Wolf
    0.08
    dept
    0.08
    {_
    0.08
    onda
    0.08
    PTH
    0.08
    omb
    0.08
     Coc
    0.08
    YPE
    0.08
    stroy
    0.08
    Activations Density 0.202%

    No Known Activations