© 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. 47885
    Prev
    Next
    INDEX
    Explanations

    requested illegal information

    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
     loos
    -0.11
    imei
    -0.11
    /misc
    -0.10
    ilos
    -0.10
     Dysfunction
    -0.10
     Graf
    -0.10
     Bridges
    -0.09
    amba
    -0.09
     prod
    -0.09
     loosely
    -0.09
    POSITIVE LOGITS
    -vers
    0.08
    lime
    0.08
     LE
    0.08
    Ordinal
    0.08
     litter
    0.08
     scramble
    0.07
    Flash
    0.07
    iana
    0.07
     subscribing
    0.07
     Pant
    0.07
    Activations Density 0.004%

    No Known Activations