© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113495
    Prev
    Next
    INDEX
    Explanations

    that's right confirmation

    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
    EG
    -0.10
     cata
    -0.10
    umat
    -0.09
    itos
    -0.09
     Libert
    -0.09
    akis
    -0.09
    ibe
    -0.08
    atz
    -0.08
     Frog
    -0.08
     nied
    -0.08
    POSITIVE LOGITS
    inine
    0.10
    corner
    0.09
     officer
    0.09
    REV
    0.09
    ych
    0.09
    hw
    0.09
     indu
    0.09
    ed
    0.08
    inet
    0.08
    afe
    0.08
    Activations Density 0.002%

    No Known Activations