© 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. 16671
    Prev
    Next
    INDEX
    Explanations

    locations and their areas

    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
    ylon
    -0.23
    intern
    -0.21
    @student
    -0.21
    ema
    -0.19
     organisers
    -0.19
    igi
    -0.18
     dish
    -0.18
     pie
    -0.18
     dubious
    -0.18
    ãĤ»ãĥ³
    -0.18
    POSITIVE LOGITS
    å¸ĤåľºéľĢæ±Ĥ
    0.24
    å¸Ĥåľºä»·æł¼
    0.24
    è¡Įä¸ļåĨħ
    0.22
     münchen
    0.22
    è¡Įä¸ļåıijå±ķ
    0.22
     erotik
    0.22
     клиенÑĤ
    0.21
     köln
    0.21
    客æĪ·æıIJä¾Ľ
    0.21
    èĮĥåĽ´åĨħ
    0.21
    Activations Density 0.079%

    No Known Activations