© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3458
    Prev
    Next
    INDEX
    Explanations

    biofuels and alternatives like ethanol, diesel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_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
    stantiate
    -0.08
    dain
    -0.08
    zas
    -0.08
     Walk
    -0.08
    è¤IJ
    -0.08
    ial
    -0.08
     maj
    -0.08
    odia
    -0.08
    _TEM
    -0.08
    èĩªåĪ¶
    -0.07
    POSITIVE LOGITS
    æĿŀ
    0.10
    ferred
    0.10
    çĤ¹è¯Ħ
    0.10
     PANEL
    0.09
    èŀ³
    0.09
     ÐŁÐµÑĤ
    0.09
    纵深
    0.08
    çĶŁäº§èĥ½åĬĽ
    0.08
    éĢłç¦ı
    0.08
    icular
    0.08
    Activations Density 0.024%

    No Known Activations