© 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. 28219
    Prev
    Next
    INDEX
    Explanations

    speaking names followed by colon

    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
     puss
    -0.11
     tol
    -0.08
     Ven
    -0.08
    /OR
    -0.08
    isha
    -0.08
    âĦ¢
    -0.08
     —↵↵
    -0.07
    (TM
    -0.07
    (__
    -0.07
     –↵↵
    -0.07
    POSITIVE LOGITS
    amina
    0.10
    asper
    0.10
    lix
    0.10
     POV
    0.09
     unl
    0.09
    Repeated
    0.09
     mouths
    0.09
     chor
    0.09
     relent
    0.09
     repeated
    0.09
    Activations Density 0.017%

    No Known Activations