© 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. 15247
    Prev
    Next
    INDEX
    Explanations

    that they/he/she

    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
    orer
    -0.10
     Barg
    -0.09
     enter
    -0.09
     literally
    -0.09
    894
    -0.09
    ones
    -0.08
     say
    -0.08
    -push
    -0.08
    %A
    -0.08
     kal
    -0.08
    POSITIVE LOGITS
     if
    0.16
     since
    0.14
     unfortunately
    0.13
    If
    0.13
     If
    0.12
    å¦Ĥæŀľ
    0.11
    	if
    0.11
     unless
    0.11
     hopefully
    0.11
    _if
    0.10
    Activations Density 0.052%

    No Known Activations