© 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. 91237
    Prev
    Next
    INDEX
    Explanations

    picture 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
    ook
    -0.10
    aines
    -0.10
    ocker
    -0.10
    yk
    -0.09
    eno
    -0.09
     recru
    -0.09
    immel
    -0.09
    released
    -0.09
     Goldman
    -0.09
    istr
    -0.09
    POSITIVE LOGITS
     of
    0.18
     showing
    0.12
     depicting
    0.11
    	of
    0.10
    [of
    0.09
     của
    0.09
     disp
    0.08
    dep
    0.08
     pf
    0.08
    §
    0.08
    Activations Density 0.207%

    No Known Activations