© 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. 29834
    Prev
    Next
    INDEX
    Explanations

    what happens when

    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
    liest
    -0.13
    -ste
    -0.11
     Ste
    -0.11
    iest
    -0.11
     terrace
    -0.11
    ounder
    -0.11
    ÑĮÑİ
    -0.11
     Terrace
    -0.11
     Terr
    -0.10
    fact
    -0.10
    POSITIVE LOGITS
     when
    0.14
    å½ĵ
    0.09
    when
    0.09
     quando
    0.08
    oba
    0.08
     Sommer
    0.08
     When
    0.08
     unavoid
    0.08
     Replay
    0.08
    	when
    0.08
    Activations Density 0.024%

    No Known Activations