© 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. 91489
    Prev
    Next
    INDEX
    Explanations

    does/do/did actions

    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
    istar
    -0.12
     Starr
    -0.11
     Saud
    -0.11
     filmer
    -0.11
     Sight
    -0.11
     Honour
    -0.10
     accordingly
    -0.10
    eward
    -0.10
     tand
    -0.10
    endra
    -0.10
    POSITIVE LOGITS
     when
    0.13
     inn
    0.11
     routinely
    0.10
     habit
    0.09
     vis
    0.09
    when
    0.09
    ucc
    0.09
     jm
    0.08
     naturally
    0.08
    /do
    0.08
    Activations Density 0.044%

    No Known Activations