© 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. 88889
    Prev
    Next
    INDEX
    Explanations

    premium

    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
    ë¥
    -0.10
    amped
    -0.10
     PrintWriter
    -0.10
     redundancy
    -0.10
    reu
    -0.09
    Performed
    -0.09
    umbn
    -0.09
    è¯Ħ论
    -0.09
     rumored
    -0.09
     COMMENTS
    -0.09
    POSITIVE LOGITS
     —↵↵
    0.09
     trat
    0.08
    TRS
    0.08
     *(*
    0.07
    legates
    0.07
    /licenses
    0.07
    rove
    0.07
     shame
    0.07
     Dro
    0.07
     privilege
    0.07
    Activations Density 0.036%

    No Known Activations