© 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. 17041
    Prev
    Next
    INDEX
    Explanations

    Sher names or endings

    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
    bjerg
    -0.08
     econom
    -0.07
    ngen
    -0.07
     rect
    -0.07
    sect
    -0.07
     consum
    -0.07
     clos
    -0.07
     whole
    -0.07
    ê²½
    -0.07
    ing
    -0.07
    POSITIVE LOGITS
    iffs
    0.16
    endas
    0.13
    iff
    0.11
    emet
    0.11
     Physician
    0.11
    ifo
    0.11
    Sher
    0.11
    iber
    0.11
    esor
    0.11
    wine
    0.11
    Activations Density 0.041%

    No Known Activations