© 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. 47995
    Prev
    Next
    INDEX
    Explanations

    about this, time stamp on

    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
     Cand
    -0.12
    ocha
    -0.11
    obil
    -0.11
     Brooks
    -0.10
    overe
    -0.10
    -l
    -0.10
    maj
    -0.10
     Bol
    -0.10
     benef
    -0.09
     bif
    -0.09
    POSITIVE LOGITS
     nevertheless
    0.11
     anyways
    0.10
    efe
    0.10
     fortunately
    0.10
     Mum
    0.10
     Fortunately
    0.09
     nonetheless
    0.09
     ref
    0.08
     cop
    0.08
    /blue
    0.08
    Activations Density 0.279%

    No Known Activations