© 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. 33036
    Prev
    Next
    INDEX
    Explanations

    especially necessary

    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
    iras
    -0.12
    onis
    -0.10
    lick
    -0.09
    wer
    -0.09
     Clips
    -0.09
    Es
    -0.09
    lice
    -0.09
     Vest
    -0.09
    /mark
    -0.09
     peg
    -0.09
    POSITIVE LOGITS
     Laf
    0.09
     Hust
    0.09
     Lambert
    0.08
    (Stack
    0.08
    -schema
    0.08
    ently
    0.08
     Moff
    0.08
    endif
    0.08
     enorme
    0.08
    idd
    0.08
    Activations Density 0.277%

    No Known Activations