© 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. 32118
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or sentiments

    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
     snug
    -0.11
    gratis
    -0.10
     excellent
    -0.10
     successfully
    -0.10
    .PREFERRED
    -0.10
     beef
    -0.10
     lil
    -0.10
     successful
    -0.10
     apprec
    -0.09
     favourable
    -0.09
    POSITIVE LOGITS
     :(
    0.28
     Worse
    0.21
     due
    0.18
     compared
    0.18
     worse
    0.17
    due
    0.17
     badly
    0.16
     unless
    0.16
     miser
    0.15
     =(
    0.15
    Activations Density 0.378%

    No Known Activations