© 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. 28381
    Prev
    Next
    INDEX
    Explanations

    searches for categories and '&'

    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
    åĴĮ
    -0.10
     Mein
    -0.09
     cialis
    -0.09
     breat
    -0.09
    ´s
    -0.09
    	and
    -0.09
     cpp
    -0.08
    [âĢ¦
    -0.08
    roz
    -0.08
    ÛĮ
    -0.08
    POSITIVE LOGITS
     &
    0.65
     &↵
    0.49
     &,
    0.46
     (&
    0.44
    (&
    0.35
     &=
    0.33
    &
    0.31
     &:
    0.30
     &(
    0.30
    -&
    0.28
    Activations Density 0.306%

    No Known Activations