© 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. 112060
    Prev
    Next
    INDEX
    Explanations

    entrances and locations

    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
    osta
    -0.11
    onga
    -0.09
    oad
    -0.09
    osti
    -0.09
     Www
    -0.09
     infiltr
    -0.09
    cke
    -0.09
    åĬŁ
    -0.09
    orda
    -0.09
     subnet
    -0.09
    POSITIVE LOGITS
     door
    0.34
     doors
    0.28
     gates
    0.24
    door
    0.23
    éŨ
    0.23
     gate
    0.23
     Door
    0.22
    Door
    0.20
     Doors
    0.19
     doorstep
    0.19
    Activations Density 0.122%

    No Known Activations