© 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. 26621
    Prev
    Next
    INDEX
    Explanations

    follow followed with

    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
     purge
    -0.09
    PDO
    -0.08
     enforced
    -0.08
    oni
    -0.08
    issan
    -0.08
    ISE
    -0.08
     direct
    -0.08
     Brent
    -0.08
    SEP
    -0.08
     Interested
    -0.08
    POSITIVE LOGITS
     closely
    0.13
     Cabr
    0.12
    çĿ
    0.11
    unda
    0.10
     frags
    0.10
     boots
    0.10
    #undef
    0.10
     conqu
    0.09
    suit
    0.09
    ifr
    0.09
    Activations Density 0.048%

    No Known Activations