© 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. 113063
    Prev
    Next
    INDEX
    Explanations

    **release of**

    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
    unk
    -0.11
     dilig
    -0.11
    hawk
    -0.10
    unc
    -0.10
    reach
    -0.10
    ossa
    -0.09
    ferences
    -0.09
    ìĦ
    -0.09
    friends
    -0.09
    ityEngine
    -0.09
    POSITIVE LOGITS
    es
    0.09
    TEAM
    0.09
     Candidate
    0.09
    irie
    0.09
     candidate
    0.09
    /reset
    0.09
    (es
    0.09
    ãģķãĤĮ
    0.09
    efa
    0.09
     into
    0.09
    Activations Density 0.080%

    No Known Activations