© 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. 30981
    Prev
    Next
    INDEX
    Explanations

    `if` clauses

    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
     freopen
    -0.11
     WHILE
    -0.10
    //---------------------------------------------------------------------------↵↵
    -0.10
     mentre
    -0.09
    AndUpdate
    -0.09
    //---------------------------------------------------------------------------↵
    -0.09
     memcmp
    -0.09
    068
    -0.09
    //{{
    -0.09
    >čč↵
    -0.09
    POSITIVE LOGITS
     if
    0.86
    if
    0.58
    	if
    0.55
     еÑģли
    0.53
    _if
    0.46
    å¦Ĥæŀľ
    0.46
     If
    0.44
     iff
    0.41
    If
    0.41
     jika
    0.40
    Activations Density 1.945%

    No Known Activations