© 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. 116695
    Prev
    Next
    INDEX
    Explanations

    html document type

    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
     length
    -0.14
    =length
    -0.12
    inch
    -0.12
    length
    -0.12
     height
    -0.11
     lengths
    -0.11
     stature
    -0.11
    éķ¿åº¦
    -0.11
    -Length
    -0.11
     Length
    -0.11
    POSITIVE LOGITS
     clothes
    0.11
     Loren
    0.10
     clothing
    0.10
     Glover
    0.10
     indo
    0.09
    idente
    0.09
     LC
    0.09
     standard
    0.09
    -standard
    0.09
     US
    0.09
    Activations Density 0.034%

    No Known Activations