© 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. 116071
    Prev
    Next
    INDEX
    Explanations

    but also

    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
     massive
    -0.09
    anco
    -0.08
     echo
    -0.08
     conv
    -0.08
     HUGE
    -0.08
     Soda
    -0.08
     bord
    -0.08
    -init
    -0.08
     forn
    -0.08
    sav
    -0.08
    POSITIVE LOGITS
     transgender
    0.13
     niche
    0.12
     minority
    0.11
    outs
    0.11
     nich
    0.11
     ethnic
    0.10
    available
    0.10
    anda
    0.10
     male
    0.10
    etes
    0.09
    Activations Density 0.001%

    No Known Activations