© 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. 17143
    Prev
    Next
    INDEX
    Explanations

    when they

    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
    æĪij
    -0.13
     I
    -0.11
    us
    -0.10
    ót
    -0.10
     me
    -0.10
    I
    -0.09
    aton
    -0.09
    quier
    -0.08
    /ne
    -0.08
    idue
    -0.08
    POSITIVE LOGITS
     they
    0.15
    they
    0.11
     bless
    0.10
     They
    0.10
    yy
    0.10
     ASAP
    0.09
    parm
    0.09
     screams
    0.09
     THEY
    0.08
     he
    0.08
    Activations Density 0.240%

    No Known Activations