© 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. 115148
    Prev
    Next
    INDEX
    Explanations

    actions of completion or presentation

    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
     Blocking
    -0.08
    bro
    -0.07
    ux
    -0.07
     o
    -0.07
    lam
    -0.07
     Favor
    -0.06
    uger
    -0.06
     Lamb
    -0.06
     lamin
    -0.06
     shielding
    -0.06
    POSITIVE LOGITS
     PROT
    0.14
    —with
    0.13
     message
    0.13
    åĽ
    0.12
     therein
    0.12
     Ree
    0.12
     arrang
    0.11
    /Peak
    0.11
     juste
    0.11
     swal
    0.11
    Activations Density 0.005%

    No Known Activations