© 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. 32083
    Prev
    Next
    INDEX
    Explanations

    your [noun]

    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
     Gest
    -0.12
    mast
    -0.11
    AGER
    -0.11
     gossip
    -0.10
    esen
    -0.10
    isd
    -0.10
     kone
    -0.10
    eder
    -0.10
     TORT
    -0.10
     Barry
    -0.10
    POSITIVE LOGITS
     impulse
    0.09
     Ank
    0.09
     deb
    0.09
    qli
    0.08
     Osw
    0.08
    ookie
    0.08
     depart
    0.07
    worthy
    0.07
     depot
    0.07
     shaken
    0.07
    Activations Density 0.001%

    No Known Activations