© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115345
    Prev
    Next
    INDEX
    Explanations

    Temple University or Temple Grandin

    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
     cui
    -0.09
    esse
    -0.09
    chw
    -0.08
    cid
    -0.08
    Temporal
    -0.08
    ROY
    -0.08
    cente
    -0.08
     CAST
    -0.08
    gard
    -0.08
    ROUGH
    -0.08
    POSITIVE LOGITS
    y
    0.13
    bard
    0.11
    omatic
    0.11
     extravag
    0.10
    loor
    0.10
    -filled
    0.10
     Pruitt
    0.10
    ism
    0.09
    -induced
    0.09
     stri
    0.09
    Activations Density 0.018%

    No Known Activations