© 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. 29878
    Prev
    Next
    INDEX
    Explanations

    volume, size, reconstruction

    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
     tongue
    -0.12
     genital
    -0.11
     vaginal
    -0.11
     dashes
    -0.11
     pussy
    -0.11
    aton
    -0.11
     tol
    -0.11
    身
    -0.10
     wrist
    -0.10
     clit
    -0.10
    POSITIVE LOGITS
     sizes
    0.14
     size
    0.13
    Size
    0.12
     Size
    0.11
    req
    0.10
     Sizes
    0.10
     flop
    0.10
     shrink
    0.10
    .size
    0.10
     transplant
    0.10
    Activations Density 0.086%

    No Known Activations