© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15131
    Prev
    Next
    INDEX
    Explanations

    Guggenheim, Gagliardi, gummy bears

    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
    åĴĮåľ°åĮº
    -0.23
    åĩºå±Ģ
    -0.20
    elijke
    -0.17
    å¹ħ
    -0.17
    åĩ¡æľ¬ç½ij
    -0.17
    äºĨèĩªå·±çļĦ
    -0.17
    éĤ¦
    -0.16
    大æłij
    -0.16
    çıĪ
    -0.16
    cps
    -0.16
    POSITIVE LOGITS
    illions
    0.22
    rä
    0.19
    tern
    0.18
    ipl
    0.17
    illion
    0.17
    laus
    0.17
    .instant
    0.16
    inh
    0.16
    rear
    0.16
    åīįæĸ¹
    0.16
    Activations Density 0.007%

    No Known Activations