© 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. 48254
    Prev
    Next
    INDEX
    Explanations

    best possible

    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
     Nad
    -0.10
     nad
    -0.09
    dle
    -0.09
     Ging
    -0.09
     closest
    -0.08
    rio
    -0.08
     Least
    -0.08
    efe
    -0.08
    uns
    -0.08
    ogn
    -0.08
    POSITIVE LOGITS
     possible
    0.24
    possible
    0.18
     Possible
    0.17
     posible
    0.15
     POSS
    0.15
    Possible
    0.15
     amount
    0.14
    _possible
    0.13
     bang
    0.13
     possibile
    0.13
    Activations Density 0.047%

    No Known Activations