© 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. 28990
    Prev
    Next
    INDEX
    Explanations

    jack (followed by specific words like off, in, or names)

    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
     bibli
    -0.10
     bek
    -0.10
     apt
    -0.10
     Picker
    -0.09
    eful
    -0.09
     Specialty
    -0.09
     gradu
    -0.08
     Bek
    -0.08
     leaps
    -0.08
     rope
    -0.08
    POSITIVE LOGITS
     off
    0.10
    -up
    0.10
     up
    0.10
    -off
    0.09
     havoc
    0.09
    obs
    0.08
     Harden
    0.08
    ruption
    0.08
    off
    0.08
    mart
    0.08
    Activations Density 0.005%

    No Known Activations