© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117584
    Prev
    Next
    INDEX
    Explanations

    say something or nothing

    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
    Negative Logits
    myp
    -0.12
    aura
    -0.11
    AXB
    -0.11
    ysz
    -0.11
    Mp
    -0.11
    abb
    -0.11
    arsi
    -0.11
    rez
    -0.11
     sweat
    -0.10
     gestures
    -0.10
    POSITIVE LOGITS
     something
    0.19
     anything
    0.18
     nothing
    0.16
     Anything
    0.12
    something
    0.12
    omething
    0.11
     Nothing
    0.10
     Something
    0.10
     nada
    0.10
     what
    0.10
    Activations Density 0.010%

    No Known Activations