© 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. 10743
    Prev
    Next
    INDEX
    Explanations

    processing completed state

    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
    åħį
    -0.21
     exp
    -0.19
    NAL
    -0.19
    ä¸ĢåĪĢ
    -0.18
     EXP
    -0.18
    rena
    -0.17
    ä¸ĭåįĪ
    -0.17
     gre
    -0.17
    chron
    -0.17
    éģĩåĪ°
    -0.17
    POSITIVE LOGITS
    çĬ¶æĢģä¸ĭ
    0.23
    çļĦ人éĥ½
    0.23
    çļĦèĦ¸
    0.22
    绦
    0.21
    æħĭ
    0.21
    åIJİçļĦ
    0.21
    çĦķ
    0.20
    æĢģ
    0.19
    าà¸ĩ
    0.18
    oded
    0.18
    Activations Density 0.091%

    No Known Activations