© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5618
    Prev
    Next
    INDEX
    Explanations

    shall not or shall be

    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
    ONO
    -0.09
    esc
    -0.09
     sens
    -0.09
    uality
    -0.09
    ylon
    -0.09
    	↵	↵
    -0.09
    eee
    -0.08
    ured
    -0.08
    ettings
    -0.08
    egas
    -0.08
    POSITIVE LOGITS
    ower
    0.13
     be
    0.13
    abus
    0.12
     endeavor
    0.10
    isto
    0.10
    own
    0.09
    owed
    0.09
    /w
    0.09
    ady
    0.09
    oret
    0.09
    Activations Density 0.023%

    No Known Activations