© 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. 28223
    Prev
    Next
    INDEX
    Explanations

    Hanan Shield or Hannan Shah

    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
    imin
    -0.08
    enth
    -0.08
     rel
    -0.08
    yi
    -0.08
     Anatomy
    -0.08
    ilers
    -0.07
     lesb
    -0.07
    bourne
    -0.07
     Longer
    -0.07
    opr
    -0.07
    POSITIVE LOGITS
     Solo
    0.15
    loser
    0.14
    Solo
    0.14
     solo
    0.13
    cko
    0.10
    anken
    0.10
     partic
    0.10
    ilton
    0.10
     cheek
    0.10
    ibal
    0.09
    Activations Density 0.081%

    No Known Activations