© 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. 7292
    Prev
    Next
    INDEX
    Explanations

    shoot, shooter, shoots

    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
     grunt
    -0.11
    hurst
    -0.11
     franch
    -0.10
    AGER
    -0.10
    aire
    -0.10
    inder
    -0.10
    ues
    -0.10
    /ne
    -0.10
    ry
    -0.10
     Entries
    -0.10
    POSITIVE LOGITS
    ings
    0.10
    /editor
    0.09
    ers
    0.09
    inh
    0.08
    s
    0.08
    erm
    0.08
    iest
    0.08
    inx
    0.08
    AndWait
    0.07
    rite
    0.07
    Activations Density 0.027%

    No Known Activations