© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15794
    Prev
    Next
    INDEX
    Explanations

    formaldehyde derivatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    uito
    -0.21
    uit
    -0.19
    ility
    -0.19
    suit
    -0.19
    æĴŃç§į
    -0.18
    æŁ¥çľĭåħ¨æĸĩ
    -0.18
    å¼ķ导
    -0.18
     maj
    -0.18
    ful
    -0.17
    andom
    -0.17
    POSITIVE LOGITS
    dehyde
    0.22
     Transparency
    0.19
    æ¢ĵ
    0.19
    pane
    0.19
    çĥĿ
    0.19
    éĢıæĺİ
    0.19
    iners
    0.18
    è£ħä¿®åħ¬åı¸
    0.18
    棺
    0.18
    éĴī
    0.18
    Activations Density 0.119%

    No Known Activations