© 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. 32283
    Prev
    Next
    INDEX
    Explanations

    choice for

    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
    enny
    -0.08
    mand
    -0.07
     Carr
    -0.07
     hob
    -0.07
    burg
    -0.07
    /trunk
    -0.06
     Kl
    -0.06
     ntohs
    -0.06
     Trump
    -0.06
     Chim
    -0.06
    POSITIVE LOGITS
    -for
    0.36
    _for
    0.33
     for
    0.32
    for
    0.32
     FOR
    0.31
    	for
    0.29
     For
    0.28
    FOR
    0.27
    For
    0.26
    _FOR
    0.25
    Activations Density 0.285%

    No Known Activations