© 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. 17754
    Prev
    Next
    INDEX
    Explanations

    corner and pocket

    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
     Rosen
    -0.10
    /y
    -0.09
    Intent
    -0.09
    /\
    -0.09
     Charg
    -0.09
    kar
    -0.09
    /int
    -0.09
     Desert
    -0.09
    oa
    -0.09
     advis
    -0.09
    POSITIVE LOGITS
     corners
    0.28
     corner
    0.22
    -corner
    0.20
     Corner
    0.17
    Corner
    0.16
    corner
    0.16
     pockets
    0.13
     nich
    0.13
     recess
    0.13
     hidden
    0.12
    Activations Density 0.007%

    No Known Activations